Search

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs, often generate garbled adversarial prompts with chaotic appearance. These adversarial prompts are difficult to transfer to other LLMs, hindering their performance in attacking unknown victim models. In this paper, for the first time, we delve into the semantic meaning embedded in garbled adversarial prompts and propose a novel method that "translates" them into coherent and human-readable natural language adversarial prompts. In this way, we can effectively uncover the semantic information that triggers vulnerabilities of the model and unambiguously transfer it to the victim model, without overlooking the adversarial information hidden in the garbled text, to enhance jailbreak attacks. It also offers a new approach to discovering effective designs for jailbreak prompts, advancing the understanding of jailbreak attacks. Experimental results demonstrate that our method significantly improves the success rate of jailbreak attacks against various safety-aligned LLMs and outperforms state-of-the-arts by large margins. With at most 10 queries, our method achieves an average attack success rate of 81.8% in attacking 7 commercial closed-source LLMs, including GPT and Claude-3 series, on HarmBench. Our method also achieves over 90% attack success rates against Llama-2-Chat models on AdvBench, despite their outstanding resistance to jailbreak attacks. Code at: https://github.com/qizhangli/Adversarial-Prompt-Translator.

Wide-angle lens distortion in portrait photography presents a significant challenge for capturing photo-realistic and aesthetically pleasing images. Such distortions are especially noticeable in facial regions. In this work, we propose encapsulating the generative face prior as a guided natural manifold to facilitate the correction of facial regions. Moreover, a notable central symmetry relationship exists in the non-face background, yet it has not been explored in the correction process. This geometry prior motivates us to introduce a novel constraint to explicitly enforce symmetry throughout the correction process, thereby contributing to a more visually appealing and natural correction in the non-face region. Experiments demonstrate that our approach outperforms previous methods by a large margin, excelling not only in quantitative measures such as line straightness and shape consistency metrics but also in terms of perceptual visual quality. All the code and models are available at https://github.com/Dev-Mrha/DualPriorsCorrection., Comment: European Conference on Computer Vision (ECCV) 2024

As large-scale models evolve, language instructions are increasingly utilized in multi-modal tasks. Due to human language habits, these instructions often contain ambiguities in real-world scenarios, necessitating the integration of visual context or common sense for accurate interpretation. However, even highly intelligent large models exhibit significant performance limitations on ambiguous instructions, where weak reasoning abilities of disambiguation can lead to catastrophic errors. To address this issue, this paper proposes Visual-O1, a multi-modal multi-turn chain-of-thought reasoning framework. It simulates human multi-modal multi-turn reasoning, providing instantial experience for highly intelligent models or empirical experience for generally intelligent models to understand ambiguous instructions. Unlike traditional methods that require models to possess high intelligence to understand long texts or perform lengthy complex reasoning, our framework does not significantly increase computational overhead and is more general and effective, even for generally intelligent models. Experiments show that our method not only significantly enhances the performance of models of different intelligence levels on ambiguous instructions but also improves their performance on general datasets. Our work highlights the potential of artificial intelligence to work like humans in real-world scenarios with uncertainty and ambiguity. We will release our data and code.

Artistic typography is a technique to visualize the meaning of input character in an imaginable and readable manner. With powerful text-to-image diffusion models, existing methods directly design the overall geometry and texture of input character, making it challenging to ensure both creativity and legibility. In this paper, we introduce a dual-branch and training-free method, namely VitaGlyph, enabling flexible artistic typography along with controllable geometry change to maintain the readability. The key insight of VitaGlyph is to treat input character as a scene composed of Subject and Surrounding, followed by rendering them under varying degrees of geometry transformation. The subject flexibly expresses the essential concept of input character, while the surrounding enriches relevant background without altering the shape. Specifically, we implement VitaGlyph through a three-phase framework: (i) Knowledge Acquisition leverages large language models to design text descriptions of subject and surrounding. (ii) Regional decomposition detects the part that most matches the subject description and divides input glyph image into subject and surrounding regions. (iii) Typography Stylization firstly refines the structure of subject region via Semantic Typography, and then separately renders the textures of Subject and Surrounding regions through Controllable Compositional Generation. Experimental results demonstrate that VitaGlyph not only achieves better artistry and readability, but also manages to depict multiple customize concepts, facilitating more creative and pleasing artistic typography generation. Our code will be made publicly at https://github.com/Carlofkl/VitaGlyph., Comment: https://github.com/Carlofkl/VitaGlyph

For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e., a defocus blurry image, an all-in-focus sharp image (and a defocus blur map), is an intricate task for the development of deblurring models. Existing image defocus deblurring methods typically rely on training data collected by specialized imaging equipment, presupposing that these pairs or triplets are perfectly aligned. However, in practical scenarios involving the collection of real-world data, direct acquisition of training triplets is infeasible, and training pairs inevitably encounter spatial misalignment issues. In this work, we introduce a reblurring-guided learning framework for single image defocus deblurring, enabling the learning of a deblurring network even with misaligned training pairs. Specifically, we first propose a baseline defocus deblurring network that utilizes spatially varying defocus blur map as degradation prior to enhance the deblurring performance. Then, to effectively learn the baseline defocus deblurring network with misaligned training pairs, our reblurring module ensures spatial consistency between the deblurred image, the reblurred image and the input blurry image by reconstructing spatially variant isotropic blur kernels. Moreover, the spatially variant blur derived from the reblurring module can serve as pseudo supervision for defocus blur map during training, interestingly transforming training pairs into training triplets. Additionally, we have collected a new dataset specifically for single image defocus deblurring (SDD) with typical misalignments, which not only substantiates our proposed method but also serves as a benchmark for future research., Comment: The source code and dataset are available at https://github.com/ssscrystal/Reblurring-guided-JDRL

We introduce LPT++, a comprehensive framework for long-tailed classification that combines parameter-efficient fine-tuning (PEFT) with a learnable model ensemble. LPT++ enhances frozen Vision Transformers (ViTs) through the integration of three core components. The first is a universal long-tailed adaptation module, which aggregates long-tailed prompts and visual adapters to adapt the pretrained model to the target domain, meanwhile improving its discriminative ability. The second is the mixture of long-tailed experts framework with a mixture-of-experts (MoE) scorer, which adaptively calculates reweighting coefficients for confidence scores from both visual-only and visual-language (VL) model experts to generate more accurate predictions. Finally, LPT++ employs a three-phase training framework, wherein each critical module is learned separately, resulting in a stable and effective long-tailed classification training paradigm. Besides, we also propose the simple version of LPT++ namely LPT, which only integrates visual-only pretrained ViT and long-tailed prompts to formulate a single model method. LPT can clearly illustrate how long-tailed prompts works meanwhile achieving comparable performance without VL pretrained models. Experiments show that, with only ~1% extra trainable parameters, LPT++ achieves comparable accuracy against all the counterparts., Comment: Extended version of arXiv:2210.01033

Text-driven 3D scene generation has seen significant advancements recently. However, most existing methods generate single-view images using generative models and then stitch them together in 3D space. This independent generation for each view often results in spatial inconsistency and implausibility in the 3D scenes. To address this challenge, we proposed a novel text-driven 3D-consistent scene generation model: SceneDreamer360. Our proposed method leverages a text-driven panoramic image generation model as a prior for 3D scene generation and employs 3D Gaussian Splatting (3DGS) to ensure consistency across multi-view panoramic images. Specifically, SceneDreamer360 enhances the fine-tuned Panfusion generator with a three-stage panoramic enhancement, enabling the generation of high-resolution, detail-rich panoramic images. During the 3D scene construction, a novel point cloud fusion initialization method is used, producing higher quality and spatially consistent point clouds. Our extensive experiments demonstrate that compared to other methods, SceneDreamer360 with its panoramic image generation and 3DGS can produce higher quality, spatially consistent, and visually appealing 3D scenes from any text prompt. Our codes are available at \url{https://github.com/liwrui/SceneDreamer360}.

With the advancement of generative models, the synthesis of different sensory elements such as music, visuals, and speech has achieved significant realism. However, the approach to generate multi-sensory outputs has not been fully explored, limiting the application on high-value scenarios such as of directing a film. Developing a movie director agent faces two major challenges: (1) Lack of parallelism and online scheduling with production steps: In the production of multi-sensory films, there are complex dependencies between different sensory elements, and the production time for each element varies. (2) Diverse needs and clear communication demands with users: Users often cannot clearly express their needs until they see a draft, which requires human-computer interaction and iteration to continually adjust and optimize the film content based on user feedback. To address these issues, we introduce AutoDirector, an interactive multi-sensory composition framework that supports long shots, special effects, music scoring, dubbing, and lip-syncing. This framework improves the efficiency of multi-sensory film production through automatic scheduling and supports the modification and improvement of interactive tasks to meet user needs. AutoDirector not only expands the application scope of human-machine collaboration but also demonstrates the potential of AI in collaborating with humans in the role of a film director to complete multi-sensory films.

Modern consumer cameras commonly employ the rolling shutter (RS) imaging mechanism, via which images are captured by scanning scenes row-by-row, resulting in RS distortion for dynamic scenes. To correct RS distortion, existing methods adopt a fully supervised learning manner that requires high framerate global shutter (GS) images as ground-truth for supervision. In this paper, we propose an enhanced Self-supervised learning framework for Dual reversed RS distortion Correction (SelfDRSC++). Firstly, we introduce a lightweight DRSC network that incorporates a bidirectional correlation matching block to refine the joint optimization of optical flows and corrected RS features, thereby improving correction performance while reducing network parameters. Subsequently, to effectively train the DRSC network, we propose a self-supervised learning strategy that ensures cycle consistency between input and reconstructed dual reversed RS images. The RS reconstruction in SelfDRSC++ can be interestingly formulated as a specialized instance of video frame interpolation, where each row in reconstructed RS images is interpolated from predicted GS images by utilizing RS distortion time maps. By achieving superior performance while simplifying the training process, SelfDRSC++ enables feasible one-stage self-supervised training. Additionally, besides start and end RS scanning time, SelfDRSC++ allows supervision of GS images at arbitrary intermediate scanning times, thus enabling the learned DRSC network to generate high framerate GS videos. The code and trained models are available at \url{https://github.com/shangwei5/SelfDRSC_plusplus}., Comment: 13 pages, 9 figures, and the code is available at \url{https://github.com/shangwei5/SelfDRSC_plusplus}

Animation line inbetweening is a crucial step in animation production aimed at enhancing animation fluidity by predicting intermediate line arts between two key frames. However, existing methods face challenges in effectively addressing sparse pixels and significant motion in line art key frames. In literature, Chamfer Distance (CD) is commonly adopted for evaluating inbetweening performance. Despite achieving favorable CD values, existing methods often generate interpolated frames with line disconnections, especially for scenarios involving large motion. Motivated by this observation, we propose a simple yet effective interpolation method for animation line inbetweening that adopts thin-plate spline-based transformation to estimate coarse motion more accurately by modeling the keypoint correspondence between two key frames, particularly for large motion scenarios. Building upon the coarse estimation, a motion refine module is employed to further enhance motion details before final frame interpolation using a simple UNet model. Furthermore, to more accurately assess the performance of animation line inbetweening, we refine the CD metric and introduce a novel metric termed Weighted Chamfer Distance, which demonstrates a higher consistency with visual perception quality. Additionally, we incorporate Earth Mover's Distance and conduct user study to provide a more comprehensive evaluation. Our method outperforms existing approaches by delivering high-quality interpolation results with enhanced fluidity. The code is available at \url{https://github.com/Tian-one/tps-inbetween}.

Arbitrary-scale video super-resolution (AVSR) aims to enhance the resolution of video frames, potentially at various scaling factors, which presents several challenges regarding spatial detail reproduction, temporal consistency, and computational complexity. In this paper, we first describe a strong baseline for AVSR by putting together three variants of elementary building blocks: 1) a flow-guided recurrent unit that aggregates spatiotemporal information from previous frames, 2) a flow-refined cross-attention unit that selects spatiotemporal information from future frames, and 3) a hyper-upsampling unit that generates scaleaware and content-independent upsampling kernels. We then introduce ST-AVSR by equipping our baseline with a multi-scale structural and textural prior computed from the pre-trained VGG network. This prior has proven effective in discriminating structure and texture across different locations and scales, which is beneficial for AVSR. Comprehensive experiments show that ST-AVSR significantly improves super-resolution quality, generalization ability, and inference speed over the state-of-theart. The code is available at https://github.com/shangwei5/ST-AVSR., Comment: Accepted by ECCV 2024, the code is available at https://github.com/shangwei5/ST-AVSR

Multi-modal crowd counting involves estimating crowd density from both visual and thermal/depth images. This task is challenging due to the significant gap between these distinct modalities. In this paper, we propose a novel approach by introducing an auxiliary broker modality and on this basis frame the task as a triple-modal learning problem. We devise a fusion-based method to generate this broker modality, leveraging a non-diffusion, lightweight counterpart of modern denoising diffusion-based fusion models. Additionally, we identify and address the ghosting effect caused by direct cross-modal image fusion in multi-modal crowd counting. Through extensive experimental evaluations on popular multi-modal crowd-counting datasets, we demonstrate the effectiveness of our method, which introduces only 4 million additional parameters, yet achieves promising results. The code is available at https://github.com/HenryCilence/Broker-Modality-Crowd-Counting., Comment: This is the preprint version of the paper and supplemental material to appear in ECCV 2024. Please cite the final published version. Code is available at https://github.com/HenryCilence/Broker-Modality-Crowd-Counting

Black-box tuning has attracted recent attention due to that the structure or inner parameters of advanced proprietary models are not accessible. Proxy-tuning provides a test-time output adjustment for tuning black-box language models. It applies the difference of the output logits before and after tuning a smaller white-box "proxy" model to improve the black-box model. However, this technique serves only as a decoding-time algorithm, leading to an inconsistency between training and testing which potentially limits overall performance. To address this problem, we introduce Consistent Proxy Tuning (CPT), a simple yet effective black-box tuning method. Different from Proxy-tuning, CPT additionally exploits the frozen large black-box model and another frozen small white-box model, ensuring consistency between training-stage optimization objective and test-time proxies. This consistency benefits Proxy-tuning and enhances model performance. Note that our method focuses solely on logit-level computation, which makes it model-agnostic and applicable to any task involving logit classification. Extensive experimental results demonstrate the superiority of our CPT in both black-box tuning of Large Language Models (LLMs) and Vision-Language Models (VLMs) across various datasets. The code is available at https://github.com/chunmeifeng/CPT., Comment: 10 pages,2 figures plus supplementary materials

Comprehensive and constructive evaluation protocols play an important role in the development of sophisticated text-to-video (T2V) generation models. Existing evaluation protocols primarily focus on temporal consistency and content continuity, yet largely ignore the dynamics of video content. Dynamics are an essential dimension for measuring the visual vividness and the honesty of video content to text prompts. In this study, we propose an effective evaluation protocol, termed DEVIL, which centers on the dynamics dimension to evaluate T2V models. For this purpose, we establish a new benchmark comprising text prompts that fully reflect multiple dynamics grades, and define a set of dynamics scores corresponding to various temporal granularities to comprehensively evaluate the dynamics of each generated video. Based on the new benchmark and the dynamics scores, we assess T2V models with the design of three metrics: dynamics range, dynamics controllability, and dynamics-based quality. Experiments show that DEVIL achieves a Pearson correlation exceeding 90% with human ratings, demonstrating its potential to advance T2V generation models. Code is available at https://github.com/MingXiangL/DEVIL.

Deep neural networks have achieved remarkable performance across various tasks when supplied with large-scale labeled data. However, the collection of labeled data can be time-consuming and labor-intensive. Semi-supervised learning (SSL), particularly through pseudo-labeling algorithms that iteratively assign pseudo-labels for self-training, offers a promising solution to mitigate the dependency of labeled data. Previous research generally applies a uniform pseudo-labeling strategy across all model layers, assuming that pseudo-labels exert uniform influence throughout. Contrasting this, our theoretical analysis and empirical experiment demonstrate feature extraction layer and linear classification layer have distinct learning behaviors in response to pseudo-labels. Based on these insights, we develop two layer-specific pseudo-label strategies, termed Grad-ReLU and Avg-Clustering. Grad-ReLU mitigates the impact of noisy pseudo-labels by removing the gradient detrimental effects of pseudo-labels in the linear classification layer. Avg-Clustering accelerates the convergence of feature extraction layer towards stable clustering centers by integrating consistent outputs. Our approach, LayerMatch, which integrates these two strategies, can avoid the severe interference of noisy pseudo-labels in the linear classification layer while accelerating the clustering capability of the feature extraction layer. Through extensive experimentation, our approach consistently demonstrates exceptional performance on standard semi-supervised learning benchmarks, achieving a significant improvement of 10.38% over baseline method and a 2.44% increase compared to state-of-the-art methods.

Deep generative models have garnered significant attention in low-level vision tasks due to their generative capabilities. Among them, diffusion model-based solutions, characterized by a forward diffusion process and a reverse denoising process, have emerged as widely acclaimed for their ability to produce samples of superior quality and diversity. This ensures the generation of visually compelling results with intricate texture information. Despite their remarkable success, a noticeable gap exists in a comprehensive survey that amalgamates these pioneering diffusion model-based works and organizes the corresponding threads. This paper proposes the comprehensive review of diffusion model-based techniques. We present three generic diffusion modeling frameworks and explore their correlations with other deep generative models, establishing the theoretical foundation. Following this, we introduce a multi-perspective categorization of diffusion models, considering both the underlying framework and the target task. Additionally, we summarize extended diffusion models applied in other tasks, including medical, remote sensing, and video scenarios. Moreover, we provide an overview of commonly used benchmarks and evaluation metrics. We conduct a thorough evaluation, encompassing both performance and efficiency, of diffusion model-based techniques in three prominent tasks. Finally, we elucidate the limitations of current diffusion models and propose seven intriguing directions for future research. This comprehensive examination aims to facilitate a profound understanding of the landscape surrounding denoising diffusion models in the context of low-level vision tasks. A curated list of diffusion model-based techniques in over 20 low-level vision tasks can be found at https://github.com/ChunmingHe/awesome-diffusion-models-in-low-level-vision., Comment: 20 pages, 23 figures, 4 tables

Diffusion models have shown superior performance on unsupervised anomaly detection tasks. Since trained with normal data only, diffusion models tend to reconstruct normal counterparts of test images with certain noises added. However, these methods treat all potential anomalies equally, which may cause two main problems. From the global perspective, the difficulty of reconstructing images with different anomalies is uneven. Therefore, instead of utilizing the same setting for all samples, we propose to predict a particular denoising step for each sample by evaluating the difference between image contents and the priors extracted from diffusion models. From the local perspective, reconstructing abnormal regions differs from normal areas even in the same image. Theoretically, the diffusion model predicts a noise for each step, typically following a standard Gaussian distribution. However, due to the difference between the anomaly and its potential normal counterpart, the predicted noise in abnormal regions will inevitably deviate from the standard Gaussian distribution. To this end, we propose introducing synthetic abnormal samples in training to encourage the diffusion models to break through the limitation of standard Gaussian distribution, and a spatial-adaptive feature fusion scheme is utilized during inference. With the above modifications, we propose a global and local adaptive diffusion model (abbreviated to GLAD) for unsupervised anomaly detection, which introduces appealing flexibility and achieves anomaly-free reconstruction while retaining as much normal information as possible. Extensive experiments are conducted on three commonly used anomaly detection datasets (MVTec-AD, MPDD, and VisA) and a printed circuit board dataset (PCB-Bank) we integrated, showing the effectiveness of the proposed method., Comment: Accepted by ECCV 2024, code and models: https://github.com/hyao1/GLAD. Due to the limitation "The abstract field cannot be longer than 1,920 characters", the abstract here is shorter than that in the PDF file

Dynamic 3D interaction has been attracting a lot of attention recently. However, creating such 4D content remains challenging. One solution is to animate 3D scenes with physics-based simulation, which requires manually assigning precise physical properties to the object or the simulated results would become unnatural. Another solution is to learn the deformation of 3D objects with the distillation of video generative models, which, however, tends to produce 3D videos with small and discontinuous motions due to the inappropriate extraction and application of physical prior. In this work, combining the strengths and complementing shortcomings of the above two solutions, we propose to learn the physical properties of a material field with video diffusion priors, and then utilize a physics-based Material-Point-Method (MPM) simulator to generate 4D content with realistic motions. In particular, we propose motion distillation sampling to emphasize video motion information during distillation. Moreover, to facilitate the optimization, we further propose a KAN-based material field with frame boosting. Experimental results demonstrate that our method enjoys more realistic motion than state-of-the-arts. Codes are released at: https://github.com/tyhuang0428/DreamPhysics., Comment: Codes are released at: https://github.com/tyhuang0428/DreamPhysics

Learning a skill generally relies on both practical experience by doer and insightful high-level guidance by instructor. Will this strategy also work well for solving complex non-convex optimization problems? Here, a common gradient-based optimizer acts like a disciplined doer, making locally optimal update at each step. Recent methods utilize large language models (LLMs) to optimize solutions for concrete problems by inferring from natural language instructions, akin to a high-level instructor. In this paper, we show that these two optimizers are complementary to each other, suggesting a collaborative optimization approach. The gradient-based optimizer and LLM-based optimizer are combined in an interleaved manner. We instruct LLMs using task descriptions and timely optimization trajectories recorded during gradient-based optimization. Inferred results from LLMs are used as restarting points for the next stage of gradient optimization. By leveraging both the locally rigorous gradient-based optimizer and the high-level deductive LLM-based optimizer, our combined optimization method consistently yields improvements over competitive baseline prompt tuning methods. Our results demonstrate the synergistic effect of conventional gradient-based optimization and the inference ability of LLMs. The code is released at https://github.com/guozix/LLM-catalyst.

Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due to the discrete nature of texts, the input gradient of LLMs struggles to precisely reflect the magnitude of loss change that results from token replacements in the prompt, leading to limited attack success rates against safety-aligned LLMs, even in the white-box setting. In this paper, we explore a new perspective on this problem, suggesting that it can be alleviated by leveraging innovations inspired in transfer-based attacks that were originally proposed for attacking black-box image classification models. For the first time, we appropriate the ideologies of effective methods among these transfer-based attacks, i.e., Skip Gradient Method and Intermediate Level Attack, into gradient-based adversarial prompt generation and achieve significant performance gains without introducing obvious computational cost. Meanwhile, by discussing mechanisms behind the gains, new insights are drawn, and proper combinations of these methods are also developed. Our empirical results show that 87% of the query-specific adversarial suffixes generated by the developed combination can induce Llama-2-7B-Chat to produce the output that exactly matches the target string on AdvBench. This match rate is 33% higher than that of a very strong baseline known as GCG, demonstrating advanced discrete optimization for adversarial prompt generation against LLMs. In addition, without introducing obvious cost, the combination achieves >30% absolute increase in attack success rates compared with GCG when generating both query-specific (38% -> 68%) and universal adversarial prompts (26.68% -> 60.32%) for attacking the Llama-2-7B-Chat model on AdvBench. Code at: https://github.com/qizhangli/Gradient-based-Jailbreak-Attacks.

In many applications, the demand arises for algorithms capable of aligning partially overlapping point sets while remaining invariant to the corresponding transformations. This research presents a method designed to meet such requirements through minimization of the objective function of the robust point matching (RPM) algorithm. First, we show that the RPM objective is a cubic polynomial. Then, through variable substitution, we transform the RPM objective to a quadratic function. Leveraging the convex envelope of bilinear monomials, we proceed to relax the resulting objective function, thus obtaining a lower bound problem that can be conveniently decomposed into distinct linear assignment and low-dimensional convex quadratic program components, both amenable to efficient optimization. Furthermore, a branch-and-bound (BnB) algorithm is devised, which solely branches over the transformation parameters, thereby boosting convergence rate. Empirical evaluations demonstrate better robustness of the proposed methodology against non-rigid deformation, positional noise, and outliers, particularly in scenarios where outliers remain distinct from inliers, when compared with prevailing state-of-the-art approaches.

Text-to-image (T2I) diffusion models have shown significant success in personalized text-to-image generation, which aims to generate novel images with human identities indicated by the reference images. Despite promising identity fidelity has been achieved by several tuning-free methods, they usually suffer from overfitting issues. The learned identity tends to entangle with irrelevant information, resulting in unsatisfied text controllability, especially on faces. In this work, we present MasterWeaver, a test-time tuning-free method designed to generate personalized images with both faithful identity fidelity and flexible editability. Specifically, MasterWeaver adopts an encoder to extract identity features and steers the image generation through additional introduced cross attention. To improve editability while maintaining identity fidelity, we propose an editing direction loss for training, which aligns the editing directions of our MasterWeaver with those of the original T2I model. Additionally, a face-augmented dataset is constructed to facilitate disentangled identity learning, and further improve the editability. Extensive experiments demonstrate that our MasterWeaver can not only generate personalized images with faithful identity, but also exhibit superiority in text controllability. Our code can be found at https://github.com/csyxwei/MasterWeaver., Comment: ECCV 2024. Our code can be found at https://github.com/csyxwei/MasterWeaver

In this paper, we consider two challenging issues in reference-based super-resolution (RefSR) for smartphone, (i) how to choose a proper reference image, and (ii) how to learn RefSR in a self-supervised manner. Particularly, we propose a novel self-supervised learning approach for real-world RefSR from observations at dual and multiple camera zooms. Firstly, considering the popularity of multiple cameras in modern smartphones, the more zoomed (telephoto) image can be naturally leveraged as the reference to guide the super-resolution (SR) of the lesser zoomed (ultra-wide) image, which gives us a chance to learn a deep network that performs SR from the dual zoomed observations (DZSR). Secondly, for self-supervised learning of DZSR, we take the telephoto image instead of an additional high-resolution image as the supervision information, and select a center patch from it as the reference to super-resolve the corresponding ultra-wide image patch. To mitigate the effect of the misalignment between ultra-wide low-resolution (LR) patch and telephoto ground-truth (GT) image during training, we first adopt patch-based optical flow alignment and then design an auxiliary-LR to guide the deforming of the warped LR features. To generate visually pleasing results, we present local overlapped sliced Wasserstein loss to better represent the perceptual difference between GT and output in the feature space. During testing, DZSR can be directly deployed to super-solve the whole ultra-wide image with the reference of the telephoto image. In addition, we further take multiple zoomed observations to explore self-supervised RefSR, and present a progressive fusion scheme for the effective utilization of reference images. Experiments show that our methods achieve better quantitative and qualitative performance against state-of-the-arts. Codes are available at https://github.com/cszhilu1998/SelfDZSR_PlusPlus., Comment: Accpted by IEEE TPAMI in 2024. Extended version of ECCV 2022 paper "Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations" (arXiv:2203.01325)

The goal of image-based virtual try-on is to generate an image of the target person naturally wearing the given clothing. However, existing methods solely focus on the frontal try-on using the frontal clothing. When the views of the clothing and person are significantly inconsistent, particularly when the person's view is non-frontal, the results are unsatisfactory. To address this challenge, we introduce Multi-View Virtual Try-ON (MV-VTON), which aims to reconstruct the dressing results from multiple views using the given clothes. Given that single-view clothes provide insufficient information for MV-VTON, we instead employ two images, i.e., the frontal and back views of the clothing, to encompass the complete view as much as possible. Moreover, we adopt diffusion models that have demonstrated superior abilities to perform our MV-VTON. In particular, we propose a view-adaptive selection method where hard-selection and soft-selection are applied to the global and local clothing feature extraction, respectively. This ensures that the clothing features are roughly fit to the person's view. Subsequently, we suggest joint attention blocks to align and fuse clothing features with person features. Additionally, we collect a MV-VTON dataset MVG, in which each person has multiple photos with diverse views and poses. Experiments show that the proposed method not only achieves state-of-the-art results on MV-VTON task using our MVG dataset, but also has superiority on frontal-view virtual try-on task using VITON-HD and DressCode datasets. Codes and datasets are publicly released at https://github.com/hywang2002/MV-VTON ., Comment: Project url: https://hywang2002.github.io/MV-VTON/

Model Weight Averaging (MWA) is a technique that seeks to enhance model's performance by averaging the weights of multiple trained models. This paper first empirically finds that 1) the vanilla MWA can benefit the class-imbalanced learning, and 2) performing model averaging in the early epochs of training yields a greater performance improvement than doing that in later epochs. Inspired by these two observations, in this paper we propose a novel MWA technique for class-imbalanced learning tasks named Iterative Model Weight Averaging (IMWA). Specifically, IMWA divides the entire training stage into multiple episodes. Within each episode, multiple models are concurrently trained from the same initialized model weight, and subsequently averaged into a singular model. Then, the weight of this average model serves as a fresh initialization for the ensuing episode, thus establishing an iterative learning paradigm. Compared to vanilla MWA, IMWA achieves higher performance improvements with the same computational cost. Moreover, IMWA can further enhance the performance of those methods employing EMA strategy, demonstrating that IMWA and EMA can complement each other. Extensive experiments on various class-imbalanced learning tasks, i.e., class-imbalanced image classification, semi-supervised class-imbalanced image classification and semi-supervised object detection tasks showcase the effectiveness of our IMWA.

This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i.e., Kuaishou/Kwai Platform. The KVQ database is divided into three parts, including 2926 videos for training, 420 videos for validation, and 854 videos for testing. The purpose is to build new benchmarks and advance the development of S-UGC VQA. The competition had 200 participants and 13 teams submitted valid solutions for the final testing phase. The proposed solutions achieved state-of-the-art performances for S-UGC VQA. The project can be found at https://github.com/lixinustc/KVQChallenge-CVPR-NTIRE2024., Comment: Accepted by CVPR2024 Workshop. The challenge report for CVPR NTIRE2024 Short-form UGC Video Quality Assessment Challenge

Despite the significant progress in image denoising, it is still challenging to restore fine-scale details while removing noise, especially in extremely low-light environments. Leveraging near-infrared (NIR) images to assist visible RGB image denoising shows the potential to address this issue, becoming a promising technology. Nonetheless, existing works still struggle with taking advantage of NIR information effectively for real-world image denoising, due to the content inconsistency between NIR-RGB images and the scarcity of real-world paired datasets. To alleviate the problem, we propose an efficient Selective Fusion Module (SFM), which can be plug-and-played into the advanced denoising networks to merge the deep NIR-RGB features. Specifically, we sequentially perform the global and local modulation for NIR and RGB features, and then integrate the two modulated features. Furthermore, we present a Real-world NIR-Assisted Image Denoising (Real-NAID) dataset, which covers diverse scenarios as well as various noise levels. Extensive experiments on both synthetic and our real-world datasets demonstrate that the proposed method achieves better results than state-of-the-art ones. The dataset, codes, and pre-trained models will be publicly available at https://github.com/ronjonxu/NAID., Comment: 10 pages

Blind-spot networks (BSN) have been prevalent network architectures in self-supervised image denoising (SSID). Existing BSNs are mostly conducted with convolution layers. Although transformers offer potential solutions to the limitations of convolutions and have demonstrated success in various image restoration tasks, their attention mechanisms may violate the blind-spot requirement, thus restricting their applicability in SSID. In this paper, we present a transformer-based blind-spot network (TBSN) by analyzing and redesigning the transformer operators that meet the blind-spot requirement. Specifically, TBSN follows the architectural principles of dilated BSNs, and incorporates spatial as well as channel self-attention layers to enhance the network capability. For spatial self-attention, an elaborate mask is applied to the attention matrix to restrict its receptive field, thus mimicking the dilated convolution. For channel self-attention, we observe that it may leak the blind-spot information when the channel number is greater than spatial size in the deep layers of multi-scale architectures. To eliminate this effect, we divide the channel into several groups and perform channel attention separately. Furthermore, we introduce a knowledge distillation strategy that distills TBSN into smaller denoisers to improve computational efficiency while maintaining performance. Extensive experiments on real-world image denoising datasets show that TBSN largely extends the receptive field and exhibits favorable performance against state-of-the-art SSID methods. The code and pre-trained models will be publicly available at https://github.com/nagejacob/TBSN.

Human visual imagination usually begins with analogies or rough sketches. For example, given an image with a girl playing guitar before a building, one may analogously imagine how it seems like if Iron Man playing guitar before Pyramid in Egypt. Nonetheless, visual condition may not be precisely aligned with the imaginary result indicated by text prompt, and existing layout-controllable text-to-image (T2I) generation models is prone to producing degraded generated results with obvious artifacts. To address this issue, we present a novel T2I generation method dubbed SmartControl, which is designed to modify the rough visual conditions for adapting to text prompt. The key idea of our SmartControl is to relax the visual condition on the areas that are conflicted with text prompts. In specific, a Control Scale Predictor (CSP) is designed to identify the conflict regions and predict the local control scales, while a dataset with text prompts and rough visual conditions is constructed for training CSP. It is worth noting that, even with a limited number (e.g., 1,000~2,000) of training samples, our SmartControl can generalize well to unseen objects. Extensive experiments on four typical visual condition types clearly show the efficacy of our SmartControl against state-of-the-arts. Source code, pre-trained models, and datasets are available at https://github.com/liuxiaoyu1104/SmartControl.

With recent advancements in visual synthesis, there is a growing risk of encountering images with detrimental effects, such as hate, discrimination, or privacy violations. The research on transforming harmful images into responsible ones remains unexplored. In this paper, we formulate a new task, responsible visual editing, which entails modifying specific concepts within an image to render it more responsible while minimizing changes. However, the concept that needs to be edited is often abstract, making it challenging to locate what needs to be modified and plan how to modify it. To tackle these challenges, we propose a Cognitive Editor (CoEditor) that harnesses the large multimodal model through a two-stage cognitive process: (1) a perceptual cognitive process to focus on what needs to be modified and (2) a behavioral cognitive process to strategize how to modify. To mitigate the negative implications of harmful images on research, we create a transparent and public dataset, AltBear, which expresses harmful information using teddy bears instead of humans. Experiments demonstrate that CoEditor can effectively comprehend abstract concepts within complex scenes and significantly surpass the performance of baseline models for responsible visual editing. We find that the AltBear dataset corresponds well to the harmful content found in real images, offering a consistent experimental evaluation, thereby providing a safer benchmark for future research. Moreover, CoEditor also shows great results in general editing. We release our code and dataset at https://github.com/kodenii/Responsible-Visual-Editing., Comment: 24 pages, 12 figures

Customized text-to-image generation aims to synthesize instantiations of user-specified concepts and has achieved unprecedented progress in handling individual concept. However, when extending to multiple customized concepts, existing methods exhibit limitations in terms of flexibility and fidelity, only accommodating the combination of limited types of models and potentially resulting in a mix of characteristics from different concepts. In this paper, we introduce the Multi-concept guidance for Multi-concept customization, termed MC$^2$, for improved flexibility and fidelity. MC$^2$ decouples the requirements for model architecture via inference time optimization, allowing the integration of various heterogeneous single-concept customized models. It adaptively refines the attention weights between visual and textual tokens, directing image regions to focus on their associated words while diminishing the impact of irrelevant ones. Extensive experiments demonstrate that MC$^2$ even surpasses previous methods that require additional training in terms of consistency with input prompt and reference images. Moreover, MC$^2$ can be extended to elevate the compositional capabilities of text-to-image generation, yielding appealing results. Code will be publicly available at https://github.com/JIANGJiaXiu/MC-2.

When zooming between dual cameras on a mobile, noticeable jumps in geometric content and image color occur in the preview, inevitably affecting the user's zoom experience. In this work, we introduce a new task, ie, dual-camera smooth zoom (DCSZ) to achieve a smooth zoom preview. The frame interpolation (FI) technique is a potential solution but struggles with ground-truth collection. To address the issue, we suggest a data factory solution where continuous virtual cameras are assembled to generate DCSZ data by rendering reconstructed 3D models of the scene. In particular, we propose a novel dual-camera smooth zoom Gaussian Splatting (ZoomGS), where a camera-specific encoding is introduced to construct a specific 3D model for each virtual camera. With the proposed data factory, we construct a synthetic dataset for DCSZ, and we utilize it to fine-tune FI models. In addition, we collect real-world dual-zoom images without ground-truth for evaluation. Extensive experiments are conducted with multiple FI methods. The results show that the fine-tuned FI models achieve a significant performance improvement over the original ones on DCSZ task. The datasets, codes, and pre-trained models will are available at https://github.com/ZcsrenlongZ/ZoomGS., Comment: 24 pages

With the development of the large-scale diffusion model, Artificial Intelligence Generated Content (AIGC) techniques are popular recently. However, how to truly make it serve our daily lives remains an open question. To this end, in this paper, we focus on employing AIGC techniques in one filed of E-commerce marketing, i.e., generating hyper-realistic advertising images for displaying user-specified shoes by human. Specifically, we propose a shoe-wearing system, called Shoe-Model, to generate plausible images of human legs interacting with the given shoes. It consists of three modules: (1) shoe wearable-area detection module (WD), (2) leg-pose synthesis module (LpS) and the final (3) shoe-wearing image generation module (SW). Them three are performed in ordered stages. Compared to baselines, our ShoeModel is shown to generalize better to different type of shoes and has ability of keeping the ID-consistency of the given shoes, as well as automatically producing reasonable interactions with human. Extensive experiments show the effectiveness of our proposed shoe-wearing system. Figure 1 shows the input and output examples of our ShoeModel., Comment: ECCV2024; 16 pages

Due to the difficulty of collecting real paired data, most existing desmoking methods train the models by synthesizing smoke, generalizing poorly to real surgical scenarios. Although a few works have explored single-image real-world desmoking in unpaired learning manners, they still encounter challenges in handling dense smoke. In this work, we address these issues together by introducing the self-supervised surgery video desmoking (SelfSVD). On the one hand, we observe that the frame captured before the activation of high-energy devices is generally clear (named pre-smoke frame, PS frame), thus it can serve as supervision for other smoky frames, making real-world self-supervised video desmoking practically feasible. On the other hand, in order to enhance the desmoking performance, we further feed the valuable information from PS frame into models, where a masking strategy and a regularization term are presented to avoid trivial solutions. In addition, we construct a real surgery video dataset for desmoking, which covers a variety of smoky scenes. Extensive experiments on the dataset show that our SelfSVD can remove smoke more effectively and efficiently while recovering more photo-realistic details than the state-of-the-art methods. The dataset, codes, and pre-trained models are available at \url{https://github.com/ZcsrenlongZ/SelfSVD}., Comment: 27 pages

Color information is the most commonly used prior knowledge for depth map super-resolution (DSR), which can provide high-frequency boundary guidance for detail restoration. However, its role and functionality in DSR have not been fully developed. In this paper, we rethink the utilization of color information and propose a hierarchical color guidance network to achieve DSR. On the one hand, the low-level detail embedding module is designed to supplement high-frequency color information of depth features in a residual mask manner at the low-level stages. On the other hand, the high-level abstract guidance module is proposed to maintain semantic consistency in the reconstruction process by using a semantic mask that encodes the global guidance information. The color information of these two dimensions plays a role in the front and back ends of the attention-based feature projection (AFP) module in a more comprehensive form. Simultaneously, the AFP module integrates the multi-scale content enhancement block and adaptive attention projection block to make full use of multi-scale information and adaptively project critical restoration information in an attention manner for DSR. Compared with the state-of-the-art methods on four benchmark datasets, our method achieves more competitive performance both qualitatively and quantitatively.

Popular convolutional neural networks mainly use paired images in a supervised way for image watermark removal. However, watermarked images do not have reference images in the real world, which results in poor robustness of image watermark removal techniques. In this paper, we propose a self-supervised convolutional neural network (CNN) in image watermark removal (SWCNN). SWCNN uses a self-supervised way to construct reference watermarked images rather than given paired training samples, according to watermark distribution. A heterogeneous U-Net architecture is used to extract more complementary structural information via simple components for image watermark removal. Taking into account texture information, a mixed loss is exploited to improve visual effects of image watermark removal. Besides, a watermark dataset is conducted. Experimental results show that the proposed SWCNN is superior to popular CNNs in image watermark removal.

Text-to-image diffusion models (T2I) have demonstrated unprecedented capabilities in creating realistic and aesthetic images. On the contrary, text-to-video diffusion models (T2V) still lag far behind in frame quality and text alignment, owing to insufficient quality and quantity of training videos. In this paper, we introduce VideoElevator, a training-free and plug-and-play method, which elevates the performance of T2V using superior capabilities of T2I. Different from conventional T2V sampling (i.e., temporal and spatial modeling), VideoElevator explicitly decomposes each sampling step into temporal motion refining and spatial quality elevating. Specifically, temporal motion refining uses encapsulated T2V to enhance temporal consistency, followed by inverting to the noise distribution required by T2I. Then, spatial quality elevating harnesses inflated T2I to directly predict less noisy latent, adding more photo-realistic details. We have conducted experiments in extensive prompts under the combination of various T2V and T2I. The results show that VideoElevator not only improves the performance of T2V baselines with foundational T2I, but also facilitates stylistic video synthesis with personalized T2I. Our code is available at https://github.com/YBYBZhang/VideoElevator., Comment: Project page: https://videoelevator.github.io Code: https://github.com/YBYBZhang/VideoElevator

In real-world conversations, the diversity and ambiguity of stickers often lead to varied interpretations based on the context, necessitating the requirement for comprehensively understanding stickers and supporting multi-tagging. To address this challenge, we introduce StickerTAG, the first multi-tag sticker dataset comprising a collected tag set with 461 tags and 13,571 sticker-tag pairs, designed to provide a deeper understanding of stickers. Recognizing multiple tags for stickers becomes particularly challenging due to sticker tags usually are fine-grained attribute aware. Hence, we propose an Attentive Attribute-oriented Prompt Learning method, ie, Att$^2$PL, to capture informative features of stickers in a fine-grained manner to better differentiate tags. Specifically, we first apply an Attribute-oriented Description Generation (ADG) module to obtain the description for stickers from four attributes. Then, a Local Re-attention (LoR) module is designed to perceive the importance of local information. Finally, we use prompt learning to guide the recognition process and adopt confidence penalty optimization to penalize the confident output distribution. Extensive experiments show that our method achieves encouraging results for all commonly used metrics.

Recent advancements in large-scale pre-trained text-to-image models have led to remarkable progress in semantic image synthesis. Nevertheless, synthesizing high-quality images with consistent semantics and layout remains a challenge. In this paper, we propose the adaPtive LAyout-semantiC fusion modulE (PLACE) that harnesses pre-trained models to alleviate the aforementioned issues. Specifically, we first employ the layout control map to faithfully represent layouts in the feature space. Subsequently, we combine the layout and semantic features in a timestep-adaptive manner to synthesize images with realistic details. During fine-tuning, we propose the Semantic Alignment (SA) loss to further enhance layout alignment. Additionally, we introduce the Layout-Free Prior Preservation (LFP) loss, which leverages unlabeled data to maintain the priors of pre-trained models, thereby improving the visual quality and semantic consistency of synthesized images. Extensive experiments demonstrate that our approach performs favorably in terms of visual quality, semantic consistency, and layout alignment. The source code and model are available at https://github.com/cszy98/PLACE/tree/main.

In this paper, we delve into the realm of vision transformers for continual semantic segmentation, a problem that has not been sufficiently explored in previous literature. Empirical investigations on the adaptation of existing frameworks to vanilla ViT reveal that incorporating visual adapters into ViTs or fine-tuning ViTs with distillation terms is advantageous for enhancing the segmentation capability of novel classes. These findings motivate us to propose Continual semantic Segmentation via Adapter-based ViT, namely ConSept. Within the simplified architecture of ViT with linear segmentation head, ConSept integrates lightweight attention-based adapters into vanilla ViTs. Capitalizing on the feature adaptation abilities of these adapters, ConSept not only retains superior segmentation ability for old classes, but also attains promising segmentation quality for novel classes. To further harness the intrinsic anti-catastrophic forgetting ability of ConSept and concurrently enhance the segmentation capabilities for both old and new classes, we propose two key strategies: distillation with a deterministic old-classes boundary for improved anti-catastrophic forgetting, and dual dice losses to regularize segmentation maps, thereby improving overall segmentation performance. Extensive experiments show the effectiveness of ConSept on multiple continual semantic segmentation benchmarks under overlapped or disjoint settings. Code will be publicly available at \url{https://github.com/DongSky/ConSept}.

In the rapidly evolving landscape of Large Language Models (LLMs), ensuring robust safety measures is paramount. To meet this crucial need, we propose \emph{SALAD-Bench}, a safety benchmark specifically designed for evaluating LLMs, attack, and defense methods. Distinguished by its breadth, SALAD-Bench transcends conventional benchmarks through its large scale, rich diversity, intricate taxonomy spanning three levels, and versatile functionalities.SALAD-Bench is crafted with a meticulous array of questions, from standard queries to complex ones enriched with attack, defense modifications and multiple-choice. To effectively manage the inherent complexity, we introduce an innovative evaluators: the LLM-based MD-Judge for QA pairs with a particular focus on attack-enhanced queries, ensuring a seamless, and reliable evaluation. Above components extend SALAD-Bench from standard LLM safety evaluation to both LLM attack and defense methods evaluation, ensuring the joint-purpose utility. Our extensive experiments shed light on the resilience of LLMs against emerging threats and the efficacy of contemporary defense tactics. Data and evaluator are released under https://github.com/OpenSafetyLab/SALAD-BENCH., Comment: Accepted at ACL 2024 Findings

Recent years have witnessed remarkable advances in artificial intelligence generated content(AIGC), with diverse input modalities, e.g., text, image, video, audio and 3D. The 3D is the most close visual modality to real-world 3D environment and carries enormous knowledge. The 3D content generation shows both academic and practical values while also presenting formidable technical challenges. This review aims to consolidate developments within the burgeoning domain of 3D content generation. Specifically, a new taxonomy is proposed that categorizes existing approaches into three types: 3D native generative methods, 2D prior-based 3D generative methods, and hybrid 3D generative methods. The survey covers approximately 60 papers spanning the major techniques. Besides, we discuss limitations of current 3D content generation techniques, and point out open challenges as well as promising directions for future work. Accompanied with this survey, we have established a project website where the resources on 3D content generation research are provided. The project page is available at https://github.com/hitcslj/Awesome-AIGC-3D., Comment: under review

Few-shot Class-Incremental Learning (FSCIL) aims to continuously learn new classes based on very limited training data without forgetting the old ones encountered. Existing studies solely relied on pure visual networks, while in this paper we solved FSCIL by leveraging the Vision-Language model (e.g., CLIP) and propose a simple yet effective framework, named Learning Prompt with Distribution-based Feature Replay (LP-DiF). We observe that simply using CLIP for zero-shot evaluation can substantially outperform the most influential methods. Then, prompt tuning technique is involved to further improve its adaptation ability, allowing the model to continually capture specific knowledge from each session. To prevent the learnable prompt from forgetting old knowledge in the new session, we propose a pseudo-feature replay approach. Specifically, we preserve the old knowledge of each class by maintaining a feature-level Gaussian distribution with a diagonal covariance matrix, which is estimated by the image features of training images and synthesized features generated from a VAE. When progressing to a new session, pseudo-features are sampled from old-class distributions combined with training images of the current session to optimize the prompt, thus enabling the model to learn new knowledge while retaining old knowledge. Experiments on three prevalent benchmarks, i.e., CIFAR100, mini-ImageNet, CUB-200, and two more challenging benchmarks, i.e., SUN-397 and CUB-200$^*$ proposed in this paper showcase the superiority of LP-DiF, achieving new state-of-the-art (SOTA) in FSCIL. Code is publicly available at https://github.com/1170300714/LP-DiF.

It is highly desired but challenging to acquire high-quality photos with clear content in low-light environments. Although multi-image processing methods (using burst, dual-exposure, or multi-exposure images) have made significant progress in addressing this issue, they typically focus on specific restoration or enhancement problems, and do not fully explore the potential of utilizing multiple images. Motivated by the fact that multi-exposure images are complementary in denoising, deblurring, high dynamic range imaging, and super-resolution, we propose to utilize exposure bracketing photography to unify image restoration and enhancement tasks in this work. Due to the difficulty in collecting real-world pairs, we suggest a solution that first pre-trains the model with synthetic paired data and then adapts it to real-world unlabeled images. In particular, a temporally modulated recurrent network (TMRNet) and self-supervised adaptation method are proposed. Moreover, we construct a data simulation pipeline to synthesize pairs and collect real-world images from 200 nighttime scenarios. Experiments on both datasets show that our method performs favorably against the state-of-the-art multi-image processing ones. The dataset, code, and pre-trained models are available at https://github.com/cszhilu1998/BracketIRE., Comment: 21 pages

In this paper, we introduce a new perspective for improving image restoration by removing degradation in the textual representations of a given degraded image. Intuitively, restoration is much easier on text modality than image one. For example, it can be easily conducted by removing degradation-related words while keeping the content-aware words. Hence, we combine the advantages of images in detail description and ones of text in degradation removal to perform restoration. To address the cross-modal assistance, we propose to map the degraded images into textual representations for removing the degradations, and then convert the restored textual representations into a guidance image for assisting image restoration. In particular, We ingeniously embed an image-to-text mapper and text restoration module into CLIP-equipped text-to-image models to generate the guidance. Then, we adopt a simple coarse-to-fine approach to dynamically inject multi-scale information from guidance to image restoration networks. Extensive experiments are conducted on various image restoration tasks, including deblurring, dehazing, deraining, and denoising, and all-in-one image restoration. The results showcase that our method outperforms state-of-the-art ones across all these tasks. The codes and models are available at \url{https://github.com/mrluin/TextualDegRemoval}.

Few-shot class-incremental learning (FSCIL) aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data. While the Contrastive Vision-Language Pre-Training (CLIP) model has been effective in addressing 2D few/zero-shot learning tasks, its direct application to 3D FSCIL faces limitations. These limitations arise from feature space misalignment and significant noise in real-world scanned 3D data. To address these challenges, we introduce two novel components: the Redundant Feature Eliminator (RFE) and the Spatial Noise Compensator (SNC). RFE aligns the feature spaces of input point clouds and their embeddings by performing a unique dimensionality reduction on the feature space of pre-trained models (PTMs), effectively eliminating redundant information without compromising semantic integrity. On the other hand, SNC is a graph-based 3D model designed to capture robust geometric information within point clouds, thereby augmenting the knowledge lost due to projection, particularly when processing real-world scanned data. Considering the imbalance in existing 3D datasets, we also propose new evaluation metrics that offer a more nuanced assessment of a 3D FSCIL model. Traditional accuracy metrics are proved to be biased; thus, our metrics focus on the model's proficiency in learning new classes while maintaining the balance between old and new classes. Experimental results on both established 3D FSCIL benchmarks and our dataset demonstrate that our approach significantly outperforms existing state-of-the-art methods.

Parameter-efficient fine-tuning (PEFT) methods have provided an effective way for adapting large vision-language models to specific tasks or scenarios. Typically, they learn a very small scale of parameters for pre-trained models in a white-box formulation, which assumes model architectures to be known and parameters to be accessible. However, large models are often not open-source due to considerations of preventing abuse or commercial factors, hence posing a barrier to the deployment of white-box PEFT methods. To alleviate the dependence on model accessibility, we introduce collaborative black-box tuning (CBBT) for both textual prompt optimization and output feature adaptation for black-box models. Specifically, considering that the backpropagation gradients are blocked, we approximate the gradients of textual prompts by analyzing the predictions with perturbed prompts. Secondly, a lightweight adapter is deployed over the output feature of the inaccessible model, further facilitating the model adaptation process. Empowered with these designs, our CBBT is extensively evaluated on eleven downstream benchmarks and achieves remarkable improvements compared to existing black-box VL adaptation methods. Code is released at https://github.com/guozix/cbbt.

Albeit progress has been made in Composed Image Retrieval (CIR), we empirically find that a certain percentage of failure retrieval results are not consistent with their relative captions. To address this issue, this work provides a Visual Question Answering (VQA) perspective to boost the performance of CIR. The resulting VQA4CIR is a post-processing approach and can be directly plugged into existing CIR methods. Given the top-C retrieved images by a CIR method, VQA4CIR aims to decrease the adverse effect of the failure retrieval results being inconsistent with the relative caption. To find the retrieved images inconsistent with the relative caption, we resort to the "QA generation to VQA" self-verification pipeline. For QA generation, we suggest fine-tuning LLM (e.g., LLaMA) to generate several pairs of questions and answers from each relative caption. We then fine-tune LVLM (e.g., LLaVA) to obtain the VQA model. By feeding the retrieved image and question to the VQA model, one can find the images inconsistent with relative caption when the answer by VQA is inconsistent with the answer in the QA pair. Consequently, the CIR performance can be boosted by modifying the ranks of inconsistently retrieved images. Experimental results show that our proposed method outperforms state-of-the-art CIR methods on the CIRR and Fashion-IQ datasets.

Customized text-to-image generation, which aims to learn user-specified concepts with a few images, has drawn significant attention recently. However, existing methods usually suffer from overfitting issues and entangle the subject-unrelated information (e.g., background and pose) with the learned concept, limiting the potential to compose concept into new scenes. To address these issues, we propose the DETEX, a novel approach that learns the disentangled concept embedding for flexible customized text-to-image generation. Unlike conventional methods that learn a single concept embedding from the given images, our DETEX represents each image using multiple word embeddings during training, i.e., a learnable image-shared subject embedding and several image-specific subject-unrelated embeddings. To decouple irrelevant attributes (i.e., background and pose) from the subject embedding, we further present several attribute mappers that encode each image as several image-specific subject-unrelated embeddings. To encourage these unrelated embeddings to capture the irrelevant information, we incorporate them with corresponding attribute words and propose a joint training strategy to facilitate the disentanglement. During inference, we only use the subject embedding for image generation, while selectively using image-specific embeddings to retain image-specified attributes. Extensive experiments demonstrate that the subject embedding obtained by our method can faithfully represent the target concept, while showing superior editability compared to the state-of-the-art methods. Our code will be made published available., Comment: 16 pages, 16 figures

3D generation has raised great attention in recent years. With the success of text-to-image diffusion models, the 2D-lifting technique becomes a promising route to controllable 3D generation. However, these methods tend to present inconsistent geometry, which is also known as the Janus problem. We observe that the problem is caused mainly by two aspects, i.e., viewpoint bias in 2D diffusion models and overfitting of the optimization objective. To address it, we propose a two-stage 2D-lifting framework, namely DreamControl, which optimizes coarse NeRF scenes as 3D self-prior and then generates fine-grained objects with control-based score distillation. Specifically, adaptive viewpoint sampling and boundary integrity metric are proposed to ensure the consistency of generated priors. The priors are then regarded as input conditions to maintain reasonable geometries, in which conditional LoRA and weighted score are further proposed to optimize detailed textures. DreamControl can generate high-quality 3D content in terms of both geometry consistency and texture fidelity. Moreover, our control-based optimization guidance is applicable to more downstream tasks, including user-guided generation and 3D animation. The project page is available at https://github.com/tyhuang0428/DreamControl., Comment: Accepted by CVPR 2024