Search

In the literature, it has been shown that the evolution of the known explicit 3D surface to the target one can be learned from 2D images using the instantaneous flow field, where the known and target 3D surfaces may largely differ in topology. We are interested in capturing 4D shapes whose topology changes largely over time. We encounter that the straightforward extension of the existing 3D-based method to the desired 4D case performs poorly. In this work, we address the challenges in extending 3D neural evolution to 4D under large topological changes by proposing two novel modifications. More precisely, we introduce (i) a new architecture to discretize and encode the deformation and learn the SDF and (ii) a technique to impose the temporal consistency. (iii) Also, we propose a rendering scheme for color prediction based on Gaussian splatting. Furthermore, to facilitate learning directly from 2D images, we propose a learning framework that can disentangle the geometry and appearance from RGB images. This method of disentanglement, while also useful for the 4D evolution problem that we are concentrating on, is also novel and valid for static scenes. Our extensive experiments on various data provide awesome results and, most importantly, open a new approach toward reconstructing challenging scenes with significant topological changes and deformations. Our source code and the dataset are publicly available at https://github.com/insait-institute/N4DE., Comment: 15 pages, 21 figures

While deep learning models are powerful tools that revolutionized many areas, they are also vulnerable to noise as they rely heavily on learning patterns and features from the exact details of the clean data. Transformers, which have become the backbone of modern vision models, are no exception. Current Discrete Wavelet Transforms (DWT) based methods do not benefit from masked autoencoder (MAE) pre-training since the inverse DWT (iDWT) introduced in these approaches is computationally inefficient and lacks compatibility with video inputs in transformer architectures. In this work, we present RobustFormer, a method that overcomes these limitations by enabling noise-robust pre-training for both images and videos; improving the efficiency of DWT-based methods by removing the need for computationally iDWT steps and simplifying the attention mechanism. To our knowledge, the proposed method is the first DWT-based method compatible with video inputs and masked pre-training. Our experiments show that MAE-based pre-training allows us to bypass the iDWT step, greatly reducing computation. Through extensive tests on benchmark datasets, RobustFormer achieves state-of-the-art results for both image and video tasks., Comment: 13 pages

The advancement of dense visual simultaneous localization and mapping (SLAM) has been greatly facilitated by the emergence of neural implicit representations. Neural implicit encoding SLAM, a typical example of which is NICE-SLAM, has recently demonstrated promising results in large-scale indoor scenes. However, these methods typically rely on temporally dense RGB-D image streams as input in order to function properly. When the input source does not support high frame rates or the camera movement is too fast, these methods often experience crashes or significant degradation in tracking and mapping accuracy. In this paper, we propose EvenNICER-SLAM, a novel approach that addresses this issue through the incorporation of event cameras. Event cameras are bio-inspired cameras that respond to intensity changes instead of absolute brightness. Specifically, we integrated an event loss backpropagation stream into the NICE-SLAM pipeline to enhance camera tracking with insufficient RGB-D input. We found through quantitative evaluation that EvenNICER-SLAM, with an inclusion of higher-frequency event image input, significantly outperforms NICE-SLAM with reduced RGB-D input frequency. Our results suggest the potential for event cameras to improve the robustness of dense SLAM systems against fast camera motion in real-world scenarios.

Recent progress in large language models and access to large-scale robotic datasets has sparked a paradigm shift in robotics models transforming them into generalists able to adapt to various tasks, scenes, and robot modalities. A large step for the community are open Vision Language Action models which showcase strong performance in a wide variety of tasks. In this work, we study the visual generalization capabilities of three existing robotic foundation models, and propose a corresponding evaluation framework. Our study shows that the existing models do not exhibit robustness to visual out-of-domain scenarios. This is potentially caused by limited variations in the training data and/or catastrophic forgetting, leading to domain limitations in the vision foundation models. We further explore OpenVLA, which uses two pre-trained vision foundation models and is, therefore, expected to generalize to out-of-domain experiments. However, we showcase catastrophic forgetting by DINO-v2 in OpenVLA through its failure to fulfill the task of depth regression. To overcome the aforementioned issue of visual catastrophic forgetting, we propose a gradual backbone reversal approach founded on model merging. This enables OpenVLA which requires the adaptation of the visual backbones during initial training -- to regain its visual generalization ability. Regaining this capability enables our ReVLA model to improve over OpenVLA by a factor of 77% and 66% for grasping and lifting in visual OOD tasks .

Current methods to learn controllers for autonomous vehicles (AVs) focus on behavioural cloning. Being trained only on exact historic data, the resulting agents often generalize poorly to novel scenarios. Simulators provide the opportunity to go beyond offline datasets, but they are still treated as complicated black boxes, only used to update the global simulation state. As a result, these RL algorithms are slow, sample-inefficient, and prior-agnostic. In this work, we leverage a differentiable simulator and design an analytic policy gradients (APG) approach to training AV controllers on the large-scale Waymo Open Motion Dataset. Our proposed framework brings the differentiable simulator into an end-to-end training loop, where gradients of the environment dynamics serve as a useful prior to help the agent learn a more grounded policy. We combine this setup with a recurrent architecture that can efficiently propagate temporal information across long simulated trajectories. This APG method allows us to learn robust, accurate, and fast policies, while only requiring widely-available expert trajectories, instead of scarce expert actions. We compare to behavioural cloning and find significant improvements in performance and robustness to noise in the dynamics, as well as overall more intuitive human-like handling.

World models are increasingly pivotal in interpreting and simulating the rules and actions of complex environments. Genie, a recent model, excels at learning from visually diverse environments but relies on costly human-collected data. We observe that their alternative method of using random agents is too limited to explore the environment. We propose to improve the model by employing reinforcement learning based agents for data generation. This approach produces diverse datasets that enhance the model's ability to adapt and perform well across various scenarios and realistic actions within the environment. In this paper, we first release the model GenieRedux - an implementation based on Genie. Additionally, we introduce GenieRedux-G, a variant that uses the agent's readily available actions to factor out action prediction uncertainty during validation. Our evaluation, including a replication of the Coinrun case study, shows that GenieRedux-G achieves superior visual fidelity and controllability using the trained agent exploration. The proposed approach is reproducable, scalable and adaptable to new types of environments. Our codebase is available at https://github.com/insait-institute/GenieRedux .

CLIP is a powerful and widely used tool for understanding images in the context of natural language descriptions to perform nuanced tasks. However, it does not offer application-specific fine-grained and structured understanding, due to its generic nature. In this work, we aim to adapt CLIP for fine-grained and structured -- in the form of tabular data -- visual understanding of museum exhibits. To facilitate such understanding we (a) collect, curate, and benchmark a dataset of 200K+ image-table pairs, and (b) develop a method that allows predicting tabular outputs for input images. Our dataset is the first of its kind in the public domain. At the same time, the proposed method is novel in leveraging CLIP's powerful representations for fine-grained and tabular understanding. The proposed method (MUZE) learns to map CLIP's image embeddings to the tabular structure by means of a proposed transformer-based parsing network (parseNet). More specifically, parseNet enables prediction of missing attribute values while integrating context from known attribute-value pairs for an input image. We show that this leads to significant improvement in accuracy. Through exhaustive experiments, we show the effectiveness of the proposed method on fine-grained and structured understanding of museum exhibits, by achieving encouraging results in a newly established benchmark. Our dataset and source-code can be found at: https://github.com/insait-institute/MUZE, Comment: Accepted to ECCV 2024

Generalist vision models aim for one and the same architecture for a variety of vision tasks. While such shared architecture may seem attractive, generalist models tend to be outperformed by their bespoken counterparts, especially in the case of panoptic segmentation. We address this problem by introducing two key contributions, without compromising the desirable properties of generalist models. These contributions are: (i) a positional-embedding (PE) based loss for improved centroid regressions; (ii) Edge Distance Sampling (EDS) for the better separation of instance boundaries. The PE-based loss facilitates a better per-pixel regression of the associated instance's centroid, whereas EDS contributes by carefully handling the void regions (caused by missing labels) and smaller instances. These two simple yet effective modifications significantly improve established baselines, while achieving state-of-the-art results among all generalist solutions. More specifically, our method achieves a panoptic quality(PQ) of 52.5 on the COCO dataset, which is an improvement of 10 points over the best model with similar approach (Painter), and is superior by 2 to the best performing diffusion-based method Pix2Seq-$\mathcal{D}$. Furthermore, we provide insights into and an in-depth analysis of our contributions through exhaustive experiments. Our source code and model weights will be made publicly available.

3D Gaussian Splatting (3DGS) has become the de facto method of 3D representation in many vision tasks. This calls for the 3D understanding directly in this representation space. To facilitate the research in this direction, we first build a large-scale dataset of 3DGS using the commonly used ShapeNet and ModelNet datasets. Our dataset ShapeSplat consists of 65K objects from 87 unique categories, whose labels are in accordance with the respective datasets. The creation of this dataset utilized the compute equivalent of 2 GPU years on a TITAN XP GPU. We utilize our dataset for unsupervised pretraining and supervised finetuning for classification and segmentation tasks. To this end, we introduce \textbf{\textit{Gaussian-MAE}}, which highlights the unique benefits of representation learning from Gaussian parameters. Through exhaustive experiments, we provide several valuable insights. In particular, we show that (1) the distribution of the optimized GS centroids significantly differs from the uniformly sampled point cloud (used for initialization) counterpart; (2) this change in distribution results in degradation in classification but improvement in segmentation tasks when using only the centroids; (3) to leverage additional Gaussian parameters, we propose Gaussian feature grouping in a normalized feature space, along with splats pooling layer, offering a tailored solution to effectively group and embed similar Gaussians, which leads to notable improvement in finetuning tasks.

Object detection, particularly open-vocabulary object detection, plays a crucial role in Earth sciences, such as environmental monitoring, natural disaster assessment, and land-use planning. However, existing open-vocabulary detectors, primarily trained on natural-world images, struggle to generalize to remote sensing images due to a significant data domain gap. Thus, this paper aims to advance the development of open-vocabulary object detection in remote sensing community. To achieve this, we first reformulate the task as Locate Anything on Earth (LAE) with the goal of detecting any novel concepts on Earth. We then developed the LAE-Label Engine which collects, auto-annotates, and unifies up to 10 remote sensing datasets creating the LAE-1M - the first large-scale remote sensing object detection dataset with broad category coverage. Using the LAE-1M, we further propose and train the novel LAE-DINO Model, the first open-vocabulary foundation object detector for the LAE task, featuring Dynamic Vocabulary Construction (DVC) and Visual-Guided Text Prompt Learning (VisGT) modules. DVC dynamically constructs vocabulary for each training batch, while VisGT maps visual features to semantic space, enhancing text features. We comprehensively conduct experiments on established remote sensing benchmark DIOR, DOTAv2.0, as well as our newly introduced 80-class LAE-80C benchmark. Results demonstrate the advantages of the LAE-1M dataset and the effectiveness of the LAE-DINO method., Comment: 10 pages, 5 figures

With the emergence of mobile devices, there is a growing demand for an efficient model to restore any degraded image for better perceptual quality. However, existing models often require specific learning modules tailored for each degradation, resulting in complex architectures and high computation costs. Different from previous work, in this paper, we propose a unified manner to achieve joint embedding by leveraging the inherent similarities across various degradations for efficient and comprehensive restoration. Specifically, we first dig into the sub-latent space of each input to analyze the key components and reweight their contributions in a gated manner. The intrinsic awareness is further integrated with contextualized attention in an X-shaped scheme, maximizing local-global intertwining. Extensive comparison on benchmarking all-in-one restoration setting validates our efficiency and effectiveness, i.e., our network sets new SOTA records while reducing model complexity by approximately -82% in trainable parameters and -85\% in FLOPs. Our code will be made publicly available at:https://github.com/Amazingren/AnyIR., Comment: Efficient Any Image Restoration

Personalized 3D avatars require an animatable representation of digital humans. Doing so instantly from monocular videos offers scalability to broad class of users and wide-scale applications. In this paper, we present a fast, simple, yet effective method for creating animatable 3D digital humans from monocular videos. Our method utilizes the efficiency of Gaussian splatting to model both 3D geometry and appearance. However, we observed that naively optimizing Gaussian splats results in inaccurate geometry, thereby leading to poor animations. This work achieves and illustrates the need of accurate 3D mesh-type modelling of the human body for animatable digitization through Gaussian splats. This is achieved by developing a novel pipeline that benefits from three key aspects: (a) implicit modelling of surface's displacements and the color's spherical harmonics; (b) binding of 3D Gaussians to the respective triangular faces of the body template; (c) a novel technique to render normals followed by their auxiliary supervision. Our exhaustive experiments on three different benchmark datasets demonstrates the state-of-the-art results of our method, in limited time settings. In fact, our method is faster by an order of magnitude (in terms of training time) than its closest competitor. At the same time, we achieve superior rendering and 3D reconstruction performance under the change of poses., Comment: 15 pages, eccv, 2024

Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved performance comparable to CL for traditional convolutional backbones. However, in 3D point cloud pretraining with ViTs, masked autoencoder (MAE) modeling remains dominant. This raises the question: Can we take the best of both worlds? To answer this question, we first empirically validate that integrating MAE-based point cloud pre-training with the standard contrastive learning paradigm, even with meticulous design, can lead to a decrease in performance. To address this limitation, we reintroduce CL into the MAE-based point cloud pre-training paradigm by leveraging the inherent contrastive properties of MAE. Specifically, rather than relying on extensive data augmentation as commonly used in the image domain, we randomly mask the input tokens twice to generate contrastive input pairs. Subsequently, a weight-sharing encoder and two identically structured decoders are utilized to perform masked token reconstruction. Additionally, we propose that for an input token masked by both masks simultaneously, the reconstructed features should be as similar as possible. This naturally establishes an explicit contrastive constraint within the generative MAE-based pre-training paradigm, resulting in our proposed method, Point-CMAE. Consequently, Point-CMAE effectively enhances the representation quality and transfer performance compared to its MAE counterpart. Experimental evaluations across various downstream applications, including classification, part segmentation, and few-shot learning, demonstrate the efficacy of our framework in surpassing state-of-the-art techniques under standard ViTs and single-modal settings. The source code and trained models are available at: https://github.com/Amazingren/Point-CMAE., Comment: Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning

Neural implicit functions have demonstrated significant importance in various areas such as computer vision, graphics. Their advantages include the ability to represent complex shapes and scenes with high fidelity, smooth interpolation capabilities, and continuous representations. Despite these benefits, the development and analysis of implicit functions have been limited by the lack of comprehensive datasets and the substantial computational resources required for their implementation and evaluation. To address these challenges, we introduce "Implicit-Zoo": a large-scale dataset requiring thousands of GPU training days designed to facilitate research and development in this field. Our dataset includes diverse 2D and 3D scenes, such as CIFAR-10, ImageNet-1K, and Cityscapes for 2D image tasks, and the OmniObject3D dataset for 3D vision tasks. We ensure high quality through strict checks, refining or filtering out low-quality data. Using Implicit-Zoo, we showcase two immediate benefits as it enables to: (1) learn token locations for transformer models; (2) directly regress 3D cameras poses of 2D images with respect to NeRF models. This in turn leads to an improved performance in all three task of image classification, semantic segmentation, and 3D pose regression, thereby unlocking new avenues for research.

With the emergence of a single large model capable of successfully solving a multitude of tasks in NLP, there has been growing research interest in achieving similar goals in computer vision. On the one hand, most of these generic models, referred to as generalist vision models, aim at producing unified outputs serving different tasks. On the other hand, some existing models aim to combine different input types (aka data modalities), which are then processed by a single large model. Yet, this step of combination remains specialized, which falls short of serving the initial ambition. In this paper, we showcase that such specialization (during unification) is unnecessary, in the context of RGB-X video object tracking. Our single model tracker, termed XTrack, can remain blind to any modality X during inference time. Our tracker employs a mixture of modal experts comprising those dedicated to shared commonality and others capable of flexibly performing reasoning conditioned on input modality. Such a design ensures the unification of input modalities towards a common latent space, without weakening the modality-specific information representation. With this idea, our training process is extremely simple, integrating multi-label classification loss with a routing function, thereby effectively aligning and unifying all modalities together, even from only paired data. Thus, during inference, we can adopt any modality without relying on the inductive bias of the modal prior and achieve generalist performance. Without any bells and whistles, our generalist and blind tracker can achieve competitive performance compared to well-established modal-specific models on 5 benchmarks across 3 auxiliary modalities, covering commonly used depth, thermal, and event data.

Reconstructing missing details from degraded low-quality inputs poses a significant challenge. Recent progress in image restoration has demonstrated the efficacy of learning large models capable of addressing various degradations simultaneously. Nonetheless, these approaches introduce considerable computational overhead and complex learning paradigms, limiting their practical utility. In response, we propose \textit{DaAIR}, an efficient All-in-One image restorer employing a Degradation-aware Learner (DaLe) in the low-rank regime to collaboratively mine shared aspects and subtle nuances across diverse degradations, generating a degradation-aware embedding. By dynamically allocating model capacity to input degradations, we realize an efficient restorer integrating holistic and specific learning within a unified model. Furthermore, DaAIR introduces a cost-efficient parameter update mechanism that enhances degradation awareness while maintaining computational efficiency. Extensive comparisons across five image degradations demonstrate that our DaAIR outperforms both state-of-the-art All-in-One models and degradation-specific counterparts, affirming our efficacy and practicality. The source will be publicly made available at https://eduardzamfir.github.io/daair/

Canonical emotions, such as happy, sad, and fearful, are easy to understand and annotate. However, emotions are often compound, e.g. happily surprised, and can be mapped to the action units (AUs) used for expressing emotions, and trivially to the canonical ones. Intuitively, emotions are continuous as represented by the arousal-valence (AV) model. An interpretable unification of these four modalities - namely, Canonical, Compound, AUs, and AV - is highly desirable, for a better representation and understanding of emotions. However, such unification remains to be unknown in the current literature. In this work, we propose an interpretable and unified emotion model, referred as C2A2. We also develop a method that leverages labels of the non-unified models to annotate the novel unified one. Finally, we modify the text-conditional diffusion models to understand continuous numbers, which are then used to generate continuous expressions using our unified emotion model. Through quantitative and qualitative experiments, we show that our generated images are rich and capture subtle expressions. Our work allows a fine-grained generation of expressions in conjunction with other textual inputs and offers a new label space for emotions at the same time., Comment: 10 pages, 9 figures, 3 tables Accepted at CVPR 2024. Project page: https://emotion-diffusion.github.io

With the widespread use of NeRF-based implicit 3D representation, the need for camera localization in the same representation becomes manifestly apparent. Doing so not only simplifies the localization process -- by avoiding an outside-the-NeRF-based localization -- but also has the potential to offer the benefit of enhanced localization. This paper studies the problem of localizing cameras in NeRF using a diffusion model for camera pose adjustment. More specifically, given a pre-trained NeRF model, we train a diffusion model that iteratively updates randomly initialized camera poses, conditioned upon the image to be localized. At test time, a new camera is localized in two steps: first, coarse localization using the proposed pose diffusion process, followed by local refinement steps of a pose inversion process in NeRF. In fact, the proposed camera localization by pose diffusion (CaLDiff) method also integrates the pose inversion steps within the diffusion process. Such integration offers significantly better localization, thanks to our downstream refinement-aware diffusion process. Our exhaustive experiments on challenging real-world data validate our method by providing significantly better results than the compared methods and the established baselines. Our source code will be made publicly available.

In this work, we address the challenge of deploying Neural Radiance Field (NeRFs) in Simultaneous Localization and Mapping (SLAM) under the condition of lacking depth information, relying solely on RGB inputs. The key to unlocking the full potential of NeRF in such a challenging context lies in the integration of real-world priors. A crucial prior we explore is the binary opacity prior of 3D space with opaque objects. To effectively incorporate this prior into the NeRF framework, we introduce a ternary-type opacity (TT) model instead, which categorizes points on a ray intersecting a surface into three regions: before, on, and behind the surface. This enables a more accurate rendering of depth, subsequently improving the performance of image warping techniques. Therefore, we further propose a novel hybrid odometry (HO) scheme that merges bundle adjustment and warping-based localization. Our integrated approach of TT and HO achieves state-of-the-art performance on synthetic and real-world datasets, in terms of both speed and accuracy. This breakthrough underscores the potential of NeRF-SLAM in navigating complex environments with high fidelity., Comment: IROS 2024

The Bird-Eye-View (BEV) is one of the most widely-used scene representations for visual perception in Autonomous Vehicles (AVs) due to its well suited compatibility to downstream tasks. For the enhanced safety of AVs, modeling perception uncertainty in BEV is crucial. Recent diffusion-based methods offer a promising approach to uncertainty modeling for visual perception but fail to effectively detect small objects in the large coverage of the BEV. Such degradation of performance can be attributed primarily to the specific network architectures and the matching strategy used when training. Here, we address this problem by combining the diffusion paradigm with current state-of-the-art 3D object detectors in BEV. We analyze the unique challenges of this approach, which do not exist with deterministic detectors, and present a simple technique based on object query interpolation that allows the model to learn positional dependencies even in the presence of the diffusion noise. Based on this, we present a diffusion-based DETR model for object detection that bears similarities to particle methods. Abundant experimentation on the NuScenes dataset shows equal or better performance for our generative approach, compared to deterministic state-of-the-art methods. Our source code will be made publicly available.

Understanding the decision-making process of drivers is one of the keys to ensuring road safety. While the driver intent and the resulting ego-motion trajectory are valuable in developing driver-assistance systems, existing methods mostly focus on the motions of other vehicles. In contrast, we focus on inferring the ego trajectory of a driver's vehicle using their gaze data. For this purpose, we first collect a new dataset, GEM, which contains high-fidelity ego-motion videos paired with drivers' eye-tracking data and GPS coordinates. Next, we develop G-MEMP, a novel multimodal ego-trajectory prediction network that combines GPS and video input with gaze data. We also propose a new metric called Path Complexity Index (PCI) to measure the trajectory complexity. We perform extensive evaluations of the proposed method on both GEM and DR(eye)VE, an existing benchmark dataset. The results show that G-MEMP significantly outperforms state-of-the-art methods in both benchmarks. Furthermore, ablation studies demonstrate over 20% improvement in average displacement using gaze data, particularly in challenging driving scenarios with a high PCI. The data, code, and models can be found at https://eth-ait.github.io/g-memp/.

In this paper, we showcase the effectiveness of optimizing monocular camera poses as a continuous function of time. The camera poses are represented using an implicit neural function which maps the given time to the corresponding camera pose. The mapped camera poses are then used for the downstream tasks where joint camera pose optimization is also required. While doing so, the network parameters -- that implicitly represent camera poses -- are optimized. We exploit the proposed method in four diverse experimental settings, namely, (1) NeRF from noisy poses; (2) NeRF from asynchronous Events; (3) Visual Simultaneous Localization and Mapping (vSLAM); and (4) vSLAM with IMUs. In all four settings, the proposed method performs significantly better than the compared baselines and the state-of-the-art methods. Additionally, using the assumption of continuous motion, changes in pose may actually live in a manifold that has lower than 6 degrees of freedom (DOF) is also realized. We call this low DOF motion representation as the \emph{intrinsic motion} and use the approach in vSLAM settings, showing impressive camera tracking performance.

In the realm of video object tracking, auxiliary modalities such as depth, thermal, or event data have emerged as valuable assets to complement the RGB trackers. In practice, most existing RGB trackers learn a single set of parameters to use them across datasets and applications. However, a similar single-model unification for multi-modality tracking presents several challenges. These challenges stem from the inherent heterogeneity of inputs -- each with modality-specific representations, the scarcity of multi-modal datasets, and the absence of all the modalities at all times. In this work, we introduce Un-Track, a Unified Tracker of a single set of parameters for any modality. To handle any modality, our method learns their common latent space through low-rank factorization and reconstruction techniques. More importantly, we use only the RGB-X pairs to learn the common latent space. This unique shared representation seamlessly binds all modalities together, enabling effective unification and accommodating any missing modality, all within a single transformer-based architecture. Our Un-Track achieves +8.1 absolute F-score gain, on the DepthTrack dataset, by introducing only +2.14 (over 21.50) GFLOPs with +6.6M (over 93M) parameters, through a simple yet efficient prompting strategy. Extensive comparisons on five benchmark datasets with different modalities show that Un-Track surpasses both SOTA unified trackers and modality-specific counterparts, validating our effectiveness and practicality. The source code is publicly available at https://github.com/Zongwei97/UnTrack., Comment: Accepted by CVPR2024

Text-to-Image (T2I) models excel at synthesizing concepts such as nouns, appearances, and styles. To enable customized content creation based on a few example images of a concept, methods such as Textual Inversion and DreamBooth invert the desired concept and enable synthesizing it in new scenes. However, inverting personalized concepts that go beyond object appearance and style (adjectives and verbs) through natural language remains a challenge. Two key characteristics of these concepts contribute to the limitations of current inversion methods. 1) Adjectives and verbs are entangled with nouns (subject) and can hinder appearance-based inversion methods, where the subject appearance leaks into the concept embedding, and 2) describing such concepts often extends beyond single word embeddings. In this study, we introduce Lego, a textual inversion method designed to invert subject-entangled concepts from a few example images. Lego disentangles concepts from their associated subjects using a simple yet effective Subject Separation step and employs a Context Loss that guides the inversion of single/multi-embedding concepts. In a thorough user study, Lego-generated concepts were preferred over 70% of the time when compared to the baseline in terms of authentically generating concepts according to a reference. Additionally, visual question answering using an LLM suggested Lego-generated concepts are better aligned with the text description of the concept.

The task of predicting 3D eye gaze from eye images can be performed either by (a) end-to-end learning for image-to-gaze mapping or by (b) fitting a 3D eye model onto images. The former case requires 3D gaze labels, while the latter requires eye semantics or landmarks to facilitate the model fitting. Although obtaining eye semantics and landmarks is relatively easy, fitting an accurate 3D eye model on them remains to be very challenging due to its ill-posed nature in general. On the other hand, obtaining large-scale 3D gaze data is cumbersome due to the required hardware setups and computational demands. In this work, we propose to predict 3D eye gaze from weak supervision of eye semantic segmentation masks and direct supervision of a few 3D gaze vectors. The proposed method combines the best of both worlds by leveraging large amounts of weak annotations--which are easy to obtain, and only a few 3D gaze vectors--which alleviate the difficulty of fitting 3D eye models on the semantic segmentation of eye images. Thus, the eye gaze vectors, used in the model fitting, are directly supervised using the few-shot gaze labels. Additionally, we propose a transformer-based network architecture, that serves as a solid baseline for our improvements. Our experiments in diverse settings illustrate the significant benefits of the proposed method, achieving about 5 degrees lower angular gaze error over the baseline, when only 0.05% 3D annotations of the training images are used. The source code is available at https://github.com/dimitris-christodoulou57/Model-aware_3D_Eye_Gaze., Comment: Accepted to ISMAR2023 as a poster paper

Modeling Neural Radiance Fields for fast-moving deformable objects from visual data alone is a challenging problem. A major issue arises due to the high deformation and low acquisition rates. To address this problem, we propose to use event cameras that offer very fast acquisition of visual change in an asynchronous manner. In this work, we develop a novel method to model the deformable neural radiance fields using RGB and event cameras. The proposed method uses the asynchronous stream of events and calibrated sparse RGB frames. In our setup, the camera pose at the individual events required to integrate them into the radiance fields remains unknown. Our method jointly optimizes these poses and the radiance field. This happens efficiently by leveraging the collection of events at once and actively sampling the events during learning. Experiments conducted on both realistically rendered graphics and real-world datasets demonstrate a significant benefit of the proposed method over the state-of-the-art and the compared baseline. This shows a promising direction for modeling deformable neural radiance fields in real-world dynamic scenes.

The local road network information is essential for autonomous navigation. This information is commonly obtained from offline HD-Maps in terms of lane graphs. However, the local road network at a given moment can be drastically different than the one given in the offline maps; due to construction works, accidents etc. Moreover, the autonomous vehicle might be at a location not covered in the offline HD-Map. Thus, online estimation of the lane graph is crucial for widespread and reliable autonomous navigation. In this work, we tackle online Bird's-Eye-View lane graph extraction from a single onboard camera image. We propose to use prior information to increase quality of the estimations. The prior is extracted from the dataset through a transformer based Wasserstein Autoencoder. The autoencoder is then used to enhance the initial lane graph estimates. This is done through optimization of the latent space vector. The optimization encourages the lane graph estimation to be logical by discouraging it to diverge from the prior distribution. We test the method on two benchmark datasets, NuScenes and Argoverse. The results show that the proposed method significantly improves the performance compared to state-of-the-art methods., Comment: ITSC 2023

Autonomous driving requires accurate local scene understanding information. To this end, autonomous agents deploy object detection and online BEV lane graph extraction methods as a part of their perception stack. In this work, we propose an architecture and loss formulation to improve the accuracy of local lane graph estimates by using 3D object detection outputs. The proposed method learns to assign the objects to centerlines by considering the centerlines as cluster centers and the objects as data points to be assigned a probability distribution over the cluster centers. This training scheme ensures direct supervision on the relationship between lanes and objects, thus leading to better performance. The proposed method improves lane graph estimation substantially over state-of-the-art methods. The extensive ablations show that our method can achieve significant performance improvements by using the outputs of existing 3D object detection methods. Since our method uses the detection outputs rather than detection method intermediate representations, a single model of our method can use any detection method at test time., Comment: ICCV 2023

Moving object segmentation (MOS) in dynamic scenes is an important, challenging, but under-explored research topic for autonomous driving, especially for sequences obtained from moving ego vehicles. Most segmentation methods leverage motion cues obtained from optical flow maps. However, since these methods are often based on optical flows that are pre-computed from successive RGB frames, this neglects the temporal consideration of events occurring within the inter-frame, consequently constraining its ability to discern objects exhibiting relative staticity but genuinely in motion. To address these limitations, we propose to exploit event cameras for better video understanding, which provide rich motion cues without relying on optical flow. To foster research in this area, we first introduce a novel large-scale dataset called DSEC-MOS for moving object segmentation from moving ego vehicles, which is the first of its kind. For benchmarking, we select various mainstream methods and rigorously evaluate them on our dataset. Subsequently, we devise EmoFormer, a novel network able to exploit the event data. For this purpose, we fuse the event temporal prior with spatial semantic maps to distinguish genuinely moving objects from the static background, adding another level of dense supervision around our object of interest. Our proposed network relies only on event data for training but does not require event input during inference, making it directly comparable to frame-only methods in terms of efficiency and more widely usable in many application cases. The exhaustive comparison highlights a significant performance improvement of our method over all other methods. The source code and dataset are publicly available at: https://github.com/ZZY-Zhou/DSEC-MOS.

Autonomous driving requires a structured understanding of the surrounding road network to navigate. One of the most common and useful representation of such an understanding is done in the form of BEV lane graphs. In this work, we use the video stream from an onboard camera for online extraction of the surrounding's lane graph. Using video, instead of a single image, as input poses both benefits and challenges in terms of combining the information from different timesteps. We study the emerged challenges using three different approaches. The first approach is a post-processing step that is capable of merging single frame lane graph estimates into a unified lane graph. The second approach uses the spatialtemporal embeddings in the transformer to enable the network to discover the best temporal aggregation strategy. Finally, the third, and the proposed method, is an early temporal aggregation through explicit BEV projection and alignment of framewise features. A single model of this proposed simple, yet effective, method can process any number of images, including one, to produce accurate lane graphs. The experiments on the Nuscenes and Argoverse datasets show the validity of all the approaches while highlighting the superiority of the proposed method. The code will be made public.

Pose-conditioned convolutional generative models struggle with high-quality 3D-consistent image generation from single-view datasets, due to their lack of sufficient 3D priors. Recently, the integration of Neural Radiance Fields (NeRFs) and generative models, such as Generative Adversarial Networks (GANs), has transformed 3D-aware generation from single-view images. NeRF-GANs exploit the strong inductive bias of neural 3D representations and volumetric rendering at the cost of higher computational complexity. This study aims at revisiting pose-conditioned 2D GANs for efficient 3D-aware generation at inference time by distilling 3D knowledge from pretrained NeRF-GANs. We propose a simple and effective method, based on re-using the well-disentangled latent space of a pre-trained NeRF-GAN in a pose-conditioned convolutional network to directly generate 3D-consistent images corresponding to the underlying 3D representations. Experiments on several datasets demonstrate that the proposed method obtains results comparable with volumetric rendering in terms of quality and 3D consistency while benefiting from the computational advantage of convolutional networks. The code will be available at: https://github.com/mshahbazi72/NeRF-GAN-Distillation

Depth cues are known to be useful for visual perception. However, direct measurement of depth is often impracticable. Fortunately, though, modern learning-based methods offer promising depth maps by inference in the wild. In this work, we adapt such depth inference models for object segmentation using the objects' "pop-out" prior in 3D. The "pop-out" is a simple composition prior that assumes objects reside on the background surface. Such compositional prior allows us to reason about objects in the 3D space. More specifically, we adapt the inferred depth maps such that objects can be localized using only 3D information. Such separation, however, requires knowledge about contact surface which we learn using the weak supervision of the segmentation mask. Our intermediate representation of contact surface, and thereby reasoning about objects purely in 3D, allows us to better transfer the depth knowledge into semantics. The proposed adaptation method uses only the depth model without needing the source data used for training, making the learning process efficient and practical. Our experiments on eight datasets of two challenging tasks, namely camouflaged object detection and salient object detection, consistently demonstrate the benefit of our method in terms of both performance and generalizability., Comment: Accepted to ICCV 2023

Novel view synthesis and 3D modeling using implicit neural field representation are shown to be very effective for calibrated multi-view cameras. Such representations are known to benefit from additional geometric and semantic supervision. Most existing methods that exploit additional supervision require dense pixel-wise labels or localized scene priors. These methods cannot benefit from high-level vague scene priors provided in terms of scenes' descriptions. In this work, we aim to leverage the geometric prior of Manhattan scenes to improve the implicit neural radiance field representations. More precisely, we assume that only the knowledge of the indoor scene (under investigation) being Manhattan is known -- with no additional information whatsoever -- with an unknown Manhattan coordinate frame. Such high-level prior is used to self-supervise the surface normals derived explicitly in the implicit neural fields. Our modeling allows us to cluster the derived normals and exploit their orthogonality constraints for self-supervision. Our exhaustive experiments on datasets of diverse indoor scenes demonstrate the significant benefit of the proposed method over the established baselines. The source code is available at https://github.com/nikola3794/normal-clustering-nerf., Comment: Paper accepted to ICCV23

We study the problem of estimating 3D shape and pose of an object in terms of keypoints, from a single 2D image. The shape and pose are learned directly from images collected by categories and their partial 2D keypoint annotations.. In this work, we first propose an end-to-end training framework for intermediate 2D keypoints extraction and final 3D shape and pose estimation. The proposed framework is then trained using only the weak supervision of the intermediate 2D keypoints. Additionally, we devise a semi-supervised training framework that benefits from both labeled and unlabeled data. To leverage the unlabeled data, we introduce and exploit the \emph{piece-wise planar hull} prior of the canonical object shape. These planar hulls are defined manually once per object category, with the help of the keypoints. On the one hand, the proposed method learns to segment these planar hulls from the labeled data. On the other hand, it simultaneously enforces the consistency between predicted keypoints and the segmented hulls on the unlabeled data. The enforced consistency allows us to efficiently use the unlabeled data for the task at hand. The proposed method achieves comparable results with fully supervised state-of-the-art methods by using only half of the annotations. Our source code will be made publicly available.

Efficiently exploiting multi-modal inputs for accurate RGB-D saliency detection is a topic of high interest. Most existing works leverage cross-modal interactions to fuse the two streams of RGB-D for intermediate features' enhancement. In this process, a practical aspect of the low quality of the available depths has not been fully considered yet. In this work, we aim for RGB-D saliency detection that is robust to the low-quality depths which primarily appear in two forms: inaccuracy due to noise and the misalignment to RGB. To this end, we propose a robust RGB-D fusion method that benefits from (1) layer-wise, and (2) trident spatial, attention mechanisms. On the one hand, layer-wise attention (LWA) learns the trade-off between early and late fusion of RGB and depth features, depending upon the depth accuracy. On the other hand, trident spatial attention (TSA) aggregates the features from a wider spatial context to address the depth misalignment problem. The proposed LWA and TSA mechanisms allow us to efficiently exploit the multi-modal inputs for saliency detection while being robust against low-quality depths. Our experiments on five benchmark datasets demonstrate that the proposed fusion method performs consistently better than the state-of-the-art fusion alternatives., Comment: Accepted to 3DV 2022

One popular group of defense techniques against adversarial attacks is based on injecting stochastic noise into the network. The main source of robustness of such stochastic defenses however is often due to the obfuscation of the gradients, offering a false sense of security. Since most of the popular adversarial attacks are optimization-based, obfuscated gradients reduce their attacking ability, while the model is still susceptible to stronger or specifically tailored adversarial attacks. Recently, five characteristics have been identified, which are commonly observed when the improvement in robustness is mainly caused by gradient obfuscation. It has since become a trend to use these five characteristics as a sufficient test, to determine whether or not gradient obfuscation is the main source of robustness. However, these characteristics do not perfectly characterize all existing cases of gradient obfuscation, and therefore can not serve as a basis for a conclusive test. In this work, we present a counterexample, showing this test is not sufficient for concluding that gradient obfuscation is not the main cause of improvements in robustness.

There have been emerging a number of benchmarks and techniques for the detection of deepfakes. However, very few works study the detection of incrementally appearing deepfakes in the real-world scenarios. To simulate the wild scenes, this paper suggests a continual deepfake detection benchmark (CDDB) over a new collection of deepfakes from both known and unknown generative models. The suggested CDDB designs multiple evaluations on the detection over easy, hard, and long sequence of deepfake tasks, with a set of appropriate measures. In addition, we exploit multiple approaches to adapt multiclass incremental learning methods, commonly used in the continual visual recognition, to the continual deepfake detection problem. We evaluate existing methods, including their adapted ones, on the proposed CDDB. Within the proposed benchmark, we explore some commonly known essentials of standard continual learning. Our study provides new insights on these essentials in the context of continual deepfake detection. The suggested CDDB is clearly more challenging than the existing benchmarks, which thus offers a suitable evaluation avenue to the future research. Both data and code are available at https://github.com/Coral79/CDDB., Comment: Accepted to WACV 2023

In most scenarios, conditional image generation can be thought of as an inversion of the image understanding process. Since generic image understanding involves solving multiple tasks, it is natural to aim at generating images via multi-conditioning. However, multi-conditional image generation is a very challenging problem due to the heterogeneity and the sparsity of the (in practice) available conditioning labels. In this work, we propose a novel neural architecture to address the problem of heterogeneity and sparsity of the spatially multi-conditional labels. Our choice of spatial conditioning, such as by semantics and depth, is driven by the promise it holds for better control of the image generation process. The proposed method uses a transformer-like architecture operating pixel-wise, which receives the available labels as input tokens to merge them in a learned homogeneous space of labels. The merged labels are then used for image generation via conditional generative adversarial training. In this process, the sparsity of the labels is handled by simply dropping the input tokens corresponding to the missing labels at the desired locations, thanks to the proposed pixel-wise operating architecture. Our experiments on three benchmark datasets demonstrate the clear superiority of our method over the state-of-the-art and compared baselines. The source code will be made publicly available.

Optimization based tracking methods have been widely successful by integrating a target model prediction module, providing effective global reasoning by minimizing an objective function. While this inductive bias integrates valuable domain knowledge, it limits the expressivity of the tracking network. In this work, we therefore propose a tracker architecture employing a Transformer-based model prediction module. Transformers capture global relations with little inductive bias, allowing it to learn the prediction of more powerful target models. We further extend the model predictor to estimate a second set of weights that are applied for accurate bounding box regression. The resulting tracker relies on training and on test frame information in order to predict all weights transductively. We train the proposed tracker end-to-end and validate its performance by conducting comprehensive experiments on multiple tracking datasets. Our tracker sets a new state of the art on three benchmarks, achieving an AUC of 68.5% on the challenging LaSOT dataset., Comment: Accepted at CVPR 2022. The code and trained models are available at https://github.com/visionml/pytracking

Previous advances in object tracking mostly reported on favorable illumination circumstances while neglecting performance at nighttime, which significantly impeded the development of related aerial robot applications. This work instead develops a novel unsupervised domain adaptation framework for nighttime aerial tracking (named UDAT). Specifically, a unique object discovery approach is provided to generate training patches from raw nighttime tracking videos. To tackle the domain discrepancy, we employ a Transformer-based bridging layer post to the feature extractor to align image features from both domains. With a Transformer day/night feature discriminator, the daytime tracking model is adversarially trained to track at night. Moreover, we construct a pioneering benchmark namely NAT2021 for unsupervised domain adaptive nighttime tracking, which comprises a test set of 180 manually annotated tracking sequences and a train set of over 276k unlabelled nighttime tracking frames. Exhaustive experiments demonstrate the robustness and domain adaptability of the proposed framework in nighttime aerial tracking. The code and benchmark are available at https://github.com/vision4robotics/UDAT., Comment: accepted by CVPR2022

Class-conditioning offers a direct means to control a Generative Adversarial Network (GAN) based on a discrete input variable. While necessary in many applications, the additional information provided by the class labels could even be expected to benefit the training of the GAN itself. On the contrary, we observe that class-conditioning causes mode collapse in limited data settings, where unconditional learning leads to satisfactory generative ability. Motivated by this observation, we propose a training strategy for class-conditional GANs (cGANs) that effectively prevents the observed mode-collapse by leveraging unconditional learning. Our training strategy starts with an unconditional GAN and gradually injects the class conditioning into the generator and the objective function. The proposed method for training cGANs with limited data results not only in stable training but also in generating high-quality images, thanks to the early-stage exploitation of the shared information across classes. We analyze the observed mode collapse problem in comprehensive experiments on four datasets. Our approach demonstrates outstanding results compared with state-of-the-art methods and established baselines. The code is available at https://github.com/mshahbazi72/transitional-cGAN

We introduce token-consistent stochastic layers in vision transformers, without causing any severe drop in performance. The added stochasticity improves network calibration, robustness and strengthens privacy. We use linear layers with token-consistent stochastic parameters inside the multilayer perceptron blocks, without altering the architecture of the transformer. The stochastic parameters are sampled from the uniform distribution, both during training and inference. The applied linear operations preserve the topological structure, formed by the set of tokens passing through the shared multilayer perceptron. This operation encourages the learning of the recognition task to rely on the topological structures of the tokens, instead of their values, which in turn offers the desired robustness and privacy of the visual features. The effectiveness of the token-consistent stochasticity is demonstrated on three different applications, namely, network calibration, adversarial robustness, and feature privacy, by boosting the performance of the respective established baselines., Comment: This article is under consideration at the Computer Vision and Image Understanding journal

In this paper, we study the representation of the shape and pose of objects using their keypoints. Therefore, we propose an end-to-end method that simultaneously detects 2D keypoints from an image and lifts them to 3D. The proposed method learns both 2D detection and 3D lifting only from 2D keypoints annotations. In addition to being end-to-end from images to 3D keypoints, our method also handles objects from multiple categories using a single neural network. We use a Transformer-based architecture to detect the keypoints, as well as to summarize the visual context of the image. This visual context information is then used while lifting the keypoints to 3D, to allow context-based reasoning for better performance. Our method can handle occlusions as well as a wide variety of object classes. Our experiments on three benchmarks demonstrate that our method performs better than the state-of-the-art. Our source code will be made publicly available.

Knowledge of the road network topology is crucial for autonomous planning and navigation. Yet, recovering such topology from a single image has only been explored in part. Furthermore, it needs to refer to the ground plane, where also the driving actions are taken. This paper aims at extracting the local road network topology, directly in the bird's-eye-view (BEV), all in a complex urban setting. The only input consists of a single onboard, forward looking camera image. We represent the road topology using a set of directed lane curves and their interactions, which are captured using their intersection points. To better capture topology, we introduce the concept of \emph{minimal cycles} and their covers. A minimal cycle is the smallest cycle formed by the directed curve segments (between two intersections). The cover is a set of curves whose segments are involved in forming a minimal cycle. We first show that the covers suffice to uniquely represent the road topology. The covers are then used to supervise deep neural networks, along with the lane curve supervision. These learn to predict the road topology from a single input image. The results on the NuScenes and Argoverse benchmarks are significantly better than those obtained with baselines. Code: https://github.com/ybarancan/TopologicalLaneGraph, Comment: CVPR 2022

Autonomous navigation requires structured representation of the road network and instance-wise identification of the other traffic agents. Since the traffic scene is defined on the ground plane, this corresponds to scene understanding in the bird's-eye-view (BEV). However, the onboard cameras of autonomous cars are customarily mounted horizontally for a better view of the surrounding, making this task very challenging. In this work, we study the problem of extracting a directed graph representing the local road network in BEV coordinates, from a single onboard camera image. Moreover, we show that the method can be extended to detect dynamic objects on the BEV plane. The semantics, locations, and orientations of the detected objects together with the road graph facilitates a comprehensive understanding of the scene. Such understanding becomes fundamental for the downstream tasks, such as path planning and navigation. We validate our approach against powerful baselines and show that our network achieves superior performance. We also demonstrate the effects of various design choices through ablation studies. Code: https://github.com/ybarancan/STSU, Comment: ICCV 2021

Traditional domain adaptive semantic segmentation addresses the task of adapting a model to a novel target domain under limited or no additional supervision. While tackling the input domain gap, the standard domain adaptation settings assume no domain change in the output space. In semantic prediction tasks, different datasets are often labeled according to different semantic taxonomies. In many real-world settings, the target domain task requires a different taxonomy than the one imposed by the source domain. We therefore introduce the more general taxonomy adaptive cross-domain semantic segmentation (TACS) problem, allowing for inconsistent taxonomies between the two domains. We further propose an approach that jointly addresses the image-level and label-level domain adaptation. On the label-level, we employ a bilateral mixed sampling strategy to augment the target domain, and a relabelling method to unify and align the label spaces. We address the image-level domain gap by proposing an uncertainty-rectified contrastive learning method, leading to more domain-invariant and class-discriminative features. We extensively evaluate the effectiveness of our framework under different TACS settings: open taxonomy, coarse-to-fine taxonomy, and implicitly-overlapping taxonomy. Our approach outperforms the previous state-of-the-art by a large margin, while being capable of adapting to target taxonomies. Our implementation is publicly available at https://github.com/ETHRuiGong/TADA., Comment: Accepted by ECCV 2022

This paper investigates the role of global context for crowd counting. Specifically, a pure transformer is used to extract features with global information from overlapping image patches. Inspired by classification, we add a context token to the input sequence, to facilitate information exchange with tokens corresponding to image patches throughout transformer layers. Due to the fact that transformers do not explicitly model the tried-and-true channel-wise interactions, we propose a token-attention module (TAM) to recalibrate encoded features through channel-wise attention informed by the context token. Beyond that, it is adopted to predict the total person count of the image through regression-token module (RTM). Extensive experiments on various datasets, including ShanghaiTech, UCF-QNRF, JHU-CROWD++ and NWPU, demonstrate that the proposed context extraction techniques can significantly improve the performance over the baselines., Comment: Accepted by Machine Intelligence Research (MIR)

We address the problem of face anti-spoofing which aims to make the face verification systems robust in the real world settings. The context of detecting live vs. spoofed face images may differ significantly in the target domain, when compared to that of labeled source domain where the model is trained. Such difference may be caused due to new and unknown spoof types, illumination conditions, scene backgrounds, among many others. These varieties of differences make the target a compound domain, thus calling for the problem of the unsupervised compound domain adaptation. We demonstrate the effectiveness of the compound domain assumption for the task of face anti-spoofing, for the first time in this work. To this end, we propose a memory augmentation method for adapting the source model to the target domain in a domain aware manner. The adaptation process is further improved by using the curriculum learning and the domain agnostic source network training approaches. The proposed method successfully adapts to the compound target domain consisting multiple new spoof types. Our experiments on multiple benchmark datasets demonstrate the superiority of the proposed method over the state-of-the-art., Comment: 9 pages, 6 figures