Search

Text-conditional image editing is a practical AIGC task that has recently emerged with great commercial and academic value. For real image editing, most diffusion model-based methods use DDIM Inversion as the first stage before editing. However, DDIM Inversion often results in reconstruction failure, leading to unsatisfactory performance for downstream editing. To address this problem, we first analyze why the reconstruction via DDIM Inversion fails. We then propose a new inversion and sampling method named Dual-Schedule Inversion. We also design a classifier to adaptively combine Dual-Schedule Inversion with different editing methods for user-friendly image editing. Our work can achieve superior reconstruction and editing performance with the following advantages: 1) It can reconstruct real images perfectly without fine-tuning, and its reversibility is guaranteed mathematically. 2) The edited object/scene conforms to the semantics of the text prompt. 3) The unedited parts of the object/scene retain the original identity.

Recent text-to-image models generate high-quality images from text prompts but lack precise control over specific components within visual concepts. Therefore, we introduce component-controllable personalization, a new task that allows users to customize and reconfigure individual components within concepts. This task faces two challenges: semantic pollution, where undesirable elements distort the concept, and semantic imbalance, which leads to disproportionate learning of the target concept and component. To address these, we design MagicTailor, a framework that uses Dynamic Masked Degradation to adaptively perturb unwanted visual semantics and Dual-Stream Balancing for more balanced learning of desired visual semantics. The experimental results show that MagicTailor outperforms existing methods in this task and enables more personalized, nuanced, and creative image generation., Comment: Project page: https://correr-zhou.github.io/MagicTailor

In this paper, we introduce MRStyle, a comprehensive framework that enables color style transfer using multi-modality reference, including image and text. To achieve a unified style feature space for both modalities, we first develop a neural network called IRStyle, which generates stylized 3D lookup tables for image reference. This is accomplished by integrating an interaction dual-mapping network with a combined supervised learning pipeline, resulting in three key benefits: elimination of visual artifacts, efficient handling of high-resolution images with low memory usage, and maintenance of style consistency even in situations with significant color style variations. For text reference, we align the text feature of stable diffusion priors with the style feature of our IRStyle to perform text-guided color style transfer (TRStyle). Our TRStyle method is highly efficient in both training and inference, producing notable open-set text-guided transfer results. Extensive experiments in both image and text settings demonstrate that our proposed method outperforms the state-of-the-art in both qualitative and quantitative evaluations.

Physics-informed deep learning has been developed as a novel paradigm for learning physical dynamics recently. While general physics-informed deep learning methods have shown early promise in learning fluid dynamics, they are difficult to generalize in arbitrary time instants in real-world scenario, where the fluid motion can be considered as a time-variant trajectory involved large-scale particles. Inspired by the advantage of diffusion model in learning the distribution of data, we first propose Pi-fusion, a physics-informed diffusion model for predicting the temporal evolution of velocity and pressure field in fluid dynamics. Physics-informed guidance sampling is proposed in the inference procedure of Pi-fusion to improve the accuracy and interpretability of learning fluid dynamics. Furthermore, we introduce a training strategy based on reciprocal learning to learn the quasiperiodical pattern of fluid motion and thus improve the generalizability of the model. The proposed approach are then evaluated on both synthetic and real-world dataset, by comparing it with state-of-the-art physics-informed deep learning methods. Experimental results show that the proposed approach significantly outperforms existing methods for predicting temporal evolution of velocity and pressure field, confirming its strong generalization by drawing probabilistic inference of forward process and physics-informed guidance sampling. The proposed Pi-fusion can also be generalized in learning other physical dynamics governed by partial differential equations.

In this paper, we introduce Matten, a cutting-edge latent diffusion model with Mamba-Attention architecture for video generation. With minimal computational cost, Matten employs spatial-temporal attention for local video content modeling and bidirectional Mamba for global video content modeling. Our comprehensive experimental evaluation demonstrates that Matten has competitive performance with the current Transformer-based and GAN-based models in benchmark performance, achieving superior FVD scores and efficiency. Additionally, we observe a direct positive correlation between the complexity of our designed model and the improvement in video quality, indicating the excellent scalability of Matten.

This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results. The aim of this challenge is to discover an effective network design or solution capable of generating brighter, clearer, and visually appealing results when dealing with a variety of conditions, including ultra-high resolution (4K and beyond), non-uniform illumination, backlighting, extreme darkness, and night scenes. A notable total of 428 participants registered for the challenge, with 22 teams ultimately making valid submissions. This paper meticulously evaluates the state-of-the-art advancements in enhancing low-light images, reflecting the significant progress and creativity in this field., Comment: NTIRE 2024 Challenge Report

Denoising diffusion models have emerged as a powerful tool for various image generation and editing tasks, facilitating the synthesis of visual content in an unconditional or input-conditional manner. The core idea behind them is learning to reverse the process of gradually adding noise to images, allowing them to generate high-quality samples from a complex distribution. In this survey, we provide an exhaustive overview of existing methods using diffusion models for image editing, covering both theoretical and practical aspects in the field. We delve into a thorough analysis and categorization of these works from multiple perspectives, including learning strategies, user-input conditions, and the array of specific editing tasks that can be accomplished. In addition, we pay special attention to image inpainting and outpainting, and explore both earlier traditional context-driven and current multimodal conditional methods, offering a comprehensive analysis of their methodologies. To further evaluate the performance of text-guided image editing algorithms, we propose a systematic benchmark, EditEval, featuring an innovative metric, LMM Score. Finally, we address current limitations and envision some potential directions for future research. The accompanying repository is released at https://github.com/SiatMMLab/Awesome-Diffusion-Model-Based-Image-Editing-Methods.

Text-conditional image editing based on large diffusion generative model has attracted the attention of both the industry and the research community. Most existing methods are non-reference editing, with the user only able to provide a source image and text prompt. However, it restricts user's control over the characteristics of editing outcome. To increase user freedom, we propose a new task called Specific Reference Condition Real Image Editing, which allows user to provide a reference image to further control the outcome, such as replacing an object with a particular one. To accomplish this, we propose a fast baseline method named SpecRef. Specifically, we design a Specific Reference Attention Controller to incorporate features from the reference image, and adopt a mask mechanism to prevent interference between editing and non-editing regions. We evaluate SpecRef on typical editing tasks and show that it can achieve satisfactory performance. The source code is available on https://github.com/jingjiqinggong/specp2p.

Recent advances in text-to-video generation have harnessed the power of diffusion models to create visually compelling content conditioned on text prompts. However, they usually encounter high computational costs and often struggle to produce videos with coherent physical motions. To tackle these issues, we propose GPT4Motion, a training-free framework that leverages the planning capability of large language models such as GPT, the physical simulation strength of Blender, and the excellent image generation ability of text-to-image diffusion models to enhance the quality of video synthesis. Specifically, GPT4Motion employs GPT-4 to generate a Blender script based on a user textual prompt, which commands Blender's built-in physics engine to craft fundamental scene components that encapsulate coherent physical motions across frames. Then these components are inputted into Stable Diffusion to generate a video aligned with the textual prompt. Experimental results on three basic physical motion scenarios, including rigid object drop and collision, cloth draping and swinging, and liquid flow, demonstrate that GPT4Motion can generate high-quality videos efficiently in maintaining motion coherency and entity consistency. GPT4Motion offers new insights in text-to-video research, enhancing its quality and broadening its horizon for further explorations.

In document processing, seal-related tasks have very large commercial applications, such as seal segmentation, seal authenticity discrimination, seal removal, and text recognition under seals. However, these seal-related tasks are highly dependent on labelled document seal datasets, resulting in very little work on these tasks. To address the lack of labelled datasets for these seal-related tasks, we propose Seal2Real, a generative method that generates a large amount of labelled document seal data, and construct a Seal-DB dataset containing 20K images with labels. In Seal2Real, we propose a prompt prior learning architecture based on a pre-trained Stable Diffusion Model that migrates the prior generative power of to our seal generation task with unsupervised training. The realistic seal generation capability greatly facilitates the performance of downstream seal-related tasks on real data. Experimental results on the Seal-DB dataset demonstrate the effectiveness of Seal2Real.

Single-shot face anti-spoofing (FAS) is a key technique for securing face recognition systems, and it requires only static images as input. However, single-shot FAS remains a challenging and under-explored problem due to two main reasons: 1) on the data side, learning FAS from RGB images is largely context-dependent, and single-shot images without additional annotations contain limited semantic information. 2) on the model side, existing single-shot FAS models are infeasible to provide proper evidence for their decisions, and FAS methods based on depth estimation require expensive per-pixel annotations. To address these issues, a large binocular NIR image dataset (BNI-FAS) is constructed and published, which contains more than 300,000 real face and plane attack images, and an Interpretable FAS Transformer (IFAST) is proposed that requires only weak supervision to produce interpretable predictions. Our IFAST can produce pixel-wise disparity maps by the proposed disparity estimation Transformer with Dynamic Matching Attention (DMA) block. Besides, a well-designed confidence map generator is adopted to cooperate with the proposed dual-teacher distillation module to obtain the final discriminant results. The comprehensive experiments show that our IFAST can achieve state-of-the-art results on BNI-FAS, proving the effectiveness of the single-shot FAS based on binocular NIR images.

Text-conditioned image editing is a recently emerged and highly practical task, and its potential is immeasurable. However, most of the concurrent methods are unable to perform action editing, i.e. they can not produce results that conform to the action semantics of the editing prompt and preserve the content of the original image. To solve the problem of action editing, we propose KV Inversion, a method that can achieve satisfactory reconstruction performance and action editing, which can solve two major problems: 1) the edited result can match the corresponding action, and 2) the edited object can retain the texture and identity of the original real image. In addition, our method does not require training the Stable Diffusion model itself, nor does it require scanning a large-scale dataset to perform time-consuming training.

Text-conditional image editing is a very useful task that has recently emerged with immeasurable potential. Most current real image editing methods first need to complete the reconstruction of the image, and then editing is carried out by various methods based on the reconstruction. Most methods use DDIM Inversion for reconstruction, however, DDIM Inversion often fails to guarantee reconstruction performance, i.e., it fails to produce results that preserve the original image content. To address the problem of reconstruction failure, we propose FEC, which consists of three sampling methods, each designed for different editing types and settings. Our three methods of FEC achieve two important goals in image editing task: 1) ensuring successful reconstruction, i.e., sampling to get a generated result that preserves the texture and features of the original real image. 2) these sampling methods can be paired with many editing methods and greatly improve the performance of these editing methods to accomplish various editing tasks. In addition, none of our sampling methods require fine-tuning of the diffusion model or time-consuming training on large-scale datasets. Hence the cost of time as well as the use of computer memory and computation can be significantly reduced.

Learning-based methods have attracted a lot of research attention and led to significant improvements in low-light image enhancement. However, most of them still suffer from two main problems: expensive computational cost in high resolution images and unsatisfactory performance in simultaneous enhancement and denoising. To address these problems, we propose BDCE, a bootstrap diffusion model that exploits the learning of the distribution of the curve parameters instead of the normal-light image itself. Specifically, we adopt the curve estimation method to handle the high-resolution images, where the curve parameters are estimated by our bootstrap diffusion model. In addition, a denoise module is applied in each iteration of curve adjustment to denoise the intermediate enhanced result of each iteration. We evaluate BDCE on commonly used benchmark datasets, and extensive experiments show that it achieves state-of-the-art qualitative and quantitative performance.

Recently, more and more research has focused on using Graph Neural Networks (GNN) to solve the Graph Similarity Computation problem (GSC), i.e., computing the Graph Edit Distance (GED) between two graphs. These methods treat GSC as an end-to-end learnable task, and the core of their architecture is the feature fusion modules to interact with the features of two graphs. Existing methods consider that graph-level embedding is difficult to capture the differences in local small structures between two graphs, and thus perform fine-grained feature fusion on node-level embedding can improve the accuracy, but leads to greater time and memory consumption in the training and inference phases. However, this paper proposes a novel graph-level fusion module Different Attention (DiffAtt), and demonstrates that graph-level fusion embeddings can substantially outperform these complex node-level fusion embeddings. We posit that the relative difference structure of the two graphs plays an important role in calculating their GED values. To this end, DiffAtt uses the difference between two graph-level embeddings as an attentional mechanism to capture the graph structural difference of the two graphs. Based on DiffAtt, a new GSC method, named Graph Edit Distance Learning via Different Attention (REDRAFT), is proposed, and experimental results demonstrate that REDRAFT achieves state-of-the-art performance in 23 out of 25 metrics in five benchmark datasets. Especially on MSE, it respectively outperforms the second best by 19.9%, 48.8%, 29.1%, 31.6%, and 2.2%. Moreover, we propose a quantitative test Remaining Subgraph Alignment Test (RESAT) to verify that among all graph-level fusion modules, the fusion embedding generated by DiffAtt can best capture the structural differences between two graphs.

Large-scale well-annotated datasets are of great importance for training an effective object detector. However, obtaining accurate bounding box annotations is laborious and demanding. Unfortunately, the resultant noisy bounding boxes could cause corrupt supervision signals and thus diminish detection performance. Motivated by the observation that the real ground-truth is usually situated in the aggregation region of the proposals assigned to a noisy ground-truth, we propose DIStribution-aware CalibratiOn (DISCO) to model the spatial distribution of proposals for calibrating supervision signals. In DISCO, spatial distribution modeling is performed to statistically extract the potential locations of objects. Based on the modeled distribution, three distribution-aware techniques, i.e., distribution-aware proposal augmentation (DA-Aug), distribution-aware box refinement (DA-Ref), and distribution-aware confidence estimation (DA-Est), are developed to improve classification, localization, and interpretability, respectively. Extensive experiments on large-scale noisy image datasets (i.e., Pascal VOC and MS-COCO) demonstrate that DISCO can achieve state-of-the-art detection performance, especially at high noise levels. Code is available at https://github.com/Correr-Zhou/DISCO., Comment: Accepted by BMVC2024

Latest diffusion-based methods for many image restoration tasks outperform traditional models, but they encounter the long-time inference problem. To tackle it, this paper proposes a Wavelet-Based Diffusion Model (WaveDM). WaveDM learns the distribution of clean images in the wavelet domain conditioned on the wavelet spectrum of degraded images after wavelet transform, which is more time-saving in each step of sampling than modeling in the spatial domain. To ensure restoration performance, a unique training strategy is proposed where the low-frequency and high-frequency spectrums are learned using distinct modules. In addition, an Efficient Conditional Sampling (ECS) strategy is developed from experiments, which reduces the number of total sampling steps to around 5. Evaluations on twelve benchmark datasets including image raindrop removal, rain steaks removal, dehazing, defocus deblurring, demoir\'eing, and denoising demonstrate that WaveDM achieves state-of-the-art performance with the efficiency that is comparable to traditional one-pass methods and over 100$\times$ faster than existing image restoration methods using vanilla diffusion models., Comment: Accepted by TMM