CVPR 2025 Papers

Modern deep neural networks have now reached human-level performance across a variety of tasks. However, unlike humans they lack the ability to explain their decisions by showing where and telling what concepts guided them. In this work, we present a unified framework for transforming any vision neural network into a spatially and conceptually interpretable model. We introduce a spatially-aware concept bottleneck layer that projects "black-box" features of pre-trained backbone models into interpretable concept maps, without requiring human labels. By training a classification layer over this bottleneck, we obtain a self-explaining model that articulates which concepts most influenced its prediction, along with heatmaps that ground them in the input image. Accordingly, we name this method "Spatially-Aware and Label-Free Concept Bottleneck Model" (SALF-CBM). Our results show that the proposed SALF-CBM: (1) Outperforms non-spatial CBM methods, as well as the original backbone, on a variety of classification tasks; (2) Produces high-quality spatial explanations, outperforming widely used heatmap-based methods on a zero-shot segmentation task; (3) Facilitates model exploration and debugging, enabling users to query specific image regions and refine the model's decisions by locally editing its concept maps.

Recent methods have made significant progress in optical flow estimation. However, the evaluation of these methods focuses mainly on improved accuracy in benchmarks and often overlooks the analysis of network robustness, which may be important in safety-critical scenarios such as autonomous driving. In this paper, we propose a novel method for robustness evaluation by modifying data from original benchmarks. Unlike previous benchmarks that focus on complex scenes, we propose to modify shape and texture of objects from the original images in order to analyze the sensitivity to these changes observed in the output. Our aim is to identify common failure cases of state-of-the-art (SOTA) methods to evaluate their robustness and understand their behaviors. We show that: Optical flow methods are more sensitive to shape changes than to texture changes; and optical flow methods tend to "remember" objects seen during training and may "ignore" the motion of unseen objects. Our experimental results and findings provide a more in-depth understanding of the behavior of recent optical flow methods.

Spatial transcriptomics (ST) are emerging technologies that reveal spatial distributions of gene expressions within tissues, serving as important ways to uncover biological insights. However, the irregular spatial profiles and variability of genes make it challenging to integrate spatial information with gene expression under a computational framework. Current algorithms mostly utilize spatial graph neural networks to encode spatial information, which may incur increased computational costs and may not be flexible enough to depict complex spatial configurations. In this study, we introduce a concise yet effective representation framework, STINR, for deciphering ST data. STINR leverages an implicit neural representation (INR) to continuously represent ST data, which efficiently characterizes spatial and slice-wise correlations of ST data by inheriting the implicit smoothness of INR. STINR allows easier integration of multiple slices and multi-omics without any alignment, and serves as a potent tool for various biological tasks including gene imputation, gene denoising, spatial domain detection, and cell-type deconvolution stemed from ST data. In particular, STINR identifies the thinnest cortex layer in the dorsolateral prefrontal cortex which previous methods were unable to achieve, and more accurately identifies tumor regions in the human squamous cell carcinoma, showcasing its practical value for biological discoveries.

We propose a novel unsupervised cross-modal homography estimation learning framework, named Split Supervised Homography estimation Network (SSHNet). SSHNet reformulates the unsupervised cross-modal homography estimation into two supervised sub-problems, each addressed by its specialized network: a homography estimation network and a modality transfer network. To realize stable training, we introduce an effective split optimization strategy to train each network separately within its respective sub-problem. We also formulate an extra homography feature space supervision to enhance feature consistency, further boosting the estimation accuracy. Moreover, we employ a simple yet effective distillation training technique to reduce model parameters and improve cross-domain generalization ability while maintaining comparable performance. The training stability of SSHNet enables its cooperation with various homography estimation architectures. Experiments reveal that the SSHNet using IHN as homography estimation network, namely SSHNet-IHN, outperforms previous unsupervised approaches by a significant margin. Even compared to supervised approaches MHN and LocalTrans, SSHNet-IHN achieves 47.4% and 85.8% mean average corner errors (MACEs) reduction on the challenging OPT-SAR dataset. Source code is available at https://github.com/Junchen-Yu/SSHNet.

The emergence of Vision Language Models (VLMs) has brought unprecedented advances in understanding multimodal information. The combination of textual and visual semantics in VLMs is highly complex and diverse, making the safety alignment of these models challenging. Furthermore, due to the limited study on the safety alignment of VLMs, there is a lack of large-scale, high-quality datasets. To address these limitations, we propose a Safety Preference Alignment dataset for Vision Language Models named SPA-VL. In terms of breadth, SPA-VL covers 6 harmfulness domains, 13 categories, and 53 subcategories, and contains 100,788 samples of the quadruple (question, image, chosen response, rejected response). In terms of depth, the responses are collected from 12 open-source (e.g., QwenVL) and closed-source (e.g., Gemini) VLMs to ensure diversity. The construction of preference data is fully automated, and the experimental results indicate that models trained with alignment techniques on the SPA-VL dataset exhibit substantial improvements in harmlessness and helpfulness while maintaining core capabilities. SPA-VL, as a large-scale, high-quality, and diverse dataset, represents a significant milestone in ensuring that VLMs achieve both harmlessness and helpfulness.

Recently, improving the residual structure and designing efficient convolutions have become important branches of lightweight visual reconstruction model design. We have observed that the feature addition mode (FAM) in existing residual structure tends to lead to slow feature learning or stagnation in feature evolution, a phenomenon we define as network inertia. In addition, although blueprint separable convolutions (BSConv) have proved the dominance of intra-kernel correlation, BSConv forces the blueprint to perform scale transformation on all channels, which may lead to incorrect intra-kernel correlation and introduce useless or disruptive features on some channels and hinder the effective propagation of features. Therefore, in this paper, we rethink the FAM and BSConv for super-light visual reconstruction framework design. First, we design a novel linking mode, called feature diversity evolution link (FDEL), which aims to alleviate the phenomenon of network inertia by reducing the retention of previous low-level features, thereby promoting the evolution of feature diversity. Second, we propose blueprint controllable convolutions (B2Conv). The B2Conv can adaptively pick accurate intra-kernel correlation in the depth-axis, effectively preventing the introduction of useless or disruptive features. Based on FDEL and B2Conv, we develop a super-light super-resolution (SR) framework SLVR for visual reconstruction. Both FDEL and B2Conv can serve as efficient plugins. Extensive experimental results demonstrate the effectiveness of our proposed B2Conv, FDEL, and SLVR. Our code will be available at https://github.com/chongningni/SLVR.

Large Multimodal Models (LMMs) have demonstrated impressive capabilities in multimodal understanding and generation, pushing forward advancements in text-to-image generation.However, achieving accurate text-image alignment for LMMs, particularly in compositional scenarios, remains challenging. Existing approaches, such as layout planning for multi-step generation and learning from human feedback or AI feedback, depend heavily on prompt engineering, costly human annotations, and continual upgrading, limiting flexibility and scalability. In this work, we introduce a model-agnostic iterative self-improvement framework (**SILMM**) that can enable LMMs to provide helpful and scalable self-feedback and optimize text-image alignment via Direct Preference Optimization (DPO). DPO can readily applied to LMMs that use discrete visual tokens as intermediate image representations; while it is less suitable for LMMs with continuous visual features, as obtaining generation probabilities is challenging.To adapt SILMM to LMMs with continuous features, we propose a diversity mechanism to obtain diverse representations and a kernel-based continuous DPO for alignment. Extensive experiments on three compositional text-to-image generation benchmarks validate the effectiveness and superiority of SILMM, showing improvements exceeding 30% on T2I-CompBench++ and around 20% on DPG-Bench.

We present SF3D, a novel method for rapid and high-quality textured object mesh reconstruction from a single image in just 0.5 seconds. Unlike most existing approaches, SF3D is explicitly trained for mesh generation, incorporating a fast UV unwrapping technique that enables swift texture generation rather than relying on vertex colors. The method also learns to predict material parameters and normal maps to enhance the visual quality of the reconstructed 3D meshes. Furthermore, SF3D integrates a delighting step to effectively remove low-frequency illumination effects, ensuring that the reconstructed meshes can be easily used in novel illumination conditions. Experiments demonstrate the superior performance of SF3D over the existing techniques

Attention-based arbitrary style transfer methods, including CNN-based, Transformer-based, and Diffusion-based, have flourished and produced high-quality stylized images. However, they perform poorly on the content and style images with the same semantics, i.e., the style of the corresponding semantic region of the generated stylized image is inconsistent with that of the style image. We argue that the root cause lies in their failure to consider the relationship between local regions and semantic regions. To address this issue, we propose a plug-and-play semantic continuous-sparse attention, dubbed SCSA, for arbitrary semantic style transfer---each query point considers certain key points in the corresponding semantic region. Specifically, semantic continuous attention ensures each query point fully attends to all the continuous key points in the same semantic region that reflect the overall style characteristics of that region; Semantic sparse attention allows each query point to focus on the most similar sparse key point in the same semantic region that exhibits the specific stylistic texture of that region. By combining the two modules, the resulting SCSA aligns the overall style of the corresponding semantic regions while transferring the vivid textures of these regions. Qualitative and quantitative results demonstrate that SCSA enables attention-based arbitrary style transfer methods to produce high-quality semantic stylized images.

This paper tackles the emerging challenge of multi-view virtual try-on, utilizing both front- and back-view clothing images as inputs. Extending frontal try-on methods to a multi-view context is not straightforward. Simply concatenating the two input views or encoding their features for a generative model, such as a diffusion model, often fails to produce satisfactory results. The main challenge lies in effectively extracting and fusing meaningful clothing features from these input views. Existing explicit warping based methods, which establish direct correspondence between input and target views, tend to introduce artifacts, particularly when there is a significant disparity between the input and target views. Conversely, implicit encoding based methods often lose spatial information about clothing, resulting in outputs that lack detail. To overcome these challenges, we propose Robust-MVTON, an end-to end method for robust and high-quality multi-view try-ons. Our approach introduces a novel cross-pose feature alignment technique to guide the fusion of clothing features and incorporates a newly designed loss function for training. With the fused multi-scale clothing features, we employ a coarse-to-fine diffusion model to generate realistic and detailed results. Extensive experiments conducted on the Deepfashion and MPV datasets affirm the superiority of our method, achieving state-of-the-art performance.

Accurately localizing audible objects based on audio-visual cues is the core objective of audio-visual segmentation. Most previous methods emphasize spatial or temporal multi-modal modeling, yet overlook challenges from ambiguous audio-visual correspondences--such as nearby visually similar but acoustically different objects and frequent shifts in objects' sounding status. Consequently, they may struggle to reliably correlate audio and visual cues, leading to over- or under-segmentation. To address these limitations, we propose a novel framework with two primary components: an audio-guided modality alignment (AMA) module and an uncertainty estimation (UE) module. Instead of indiscriminately correlating audio-visual cues through a global attention mechanism, AMA performs audio-visual interactions within multiple groups and consolidates group features into compact representations based on their responsiveness to audio cues, effectively directing the model's attention to audio-relevant areas. Leveraging contrastive learning, AMA further distinguishes sounding regions from silent areas by treating features with strong audio responses as positive samples and weaker responses as negatives. Additionally, UE integrates spatial and temporal information to identify high-uncertainty regions caused by frequent changes in sound state, reducing prediction errors by lowering confidence in these areas. Experimental results demonstrate that our approach achieves superior accuracy compared to existing state-of-the-art methods, particularly in challenging scenarios where traditional approaches struggle to maintain reliable segmentation.

Rip currents are strong, localized and narrow currents of water that flow outwards into the sea, causing numerous beach-related injuries and fatalities worldwide. Accurate identification of rip currents remains challenging due to their amorphous nature and the lack of annotated data, which often requires expert knowledge. To address these issues, we present RipVIS, a large-scale video instance segmentation benchmark explicitly designed for rip current segmentation. RipVIS is an order of magnitude larger than previous datasets, featuring 184 videos (212,328 frames), of which 150 videos (163,528 frames) are with rip currents, collected from various sources, including drones, mobile phones, and fixed beach cameras. Our dataset encompasses diverse visual contexts, such as wave-breaking patterns, sediment flows, and water color variations, across multiple global locations, including USA, Mexico, Costa Rica, Portugal, Italy, Greece, Romania, Sri Lanka, Australia and New Zealand. Most videos are annotated at 5 FPS to ensure accuracy in dynamic scenarios, supplemented by an additional 34 videos (48,800 frames) without rip currents. We conduct comprehensive experiments with Mask R-CNN, Cascade Mask R-CNN, SparseInst and YOLO11, fine-tuning these models for the task of rip current segmentation. Results are reported in terms of multiple metrics, with a particular focus on the F2 score to prioritize recall and reduce false negatives. To enhance segmentation performance, we introduce a novel post-processing step based on Temporal Confidence Aggregation (TCA). RipVIS aims to set a new standard for rip current segmentation, contributing towards safer beach environments. We offer a benchmark website to share data, models, and results with the research community, encouraging ongoing collaboration and future contributions, at https://ripvis.ai.

Recently, enhancing image quality in the original RAW domain has garnered significant attention, with denoising and reconstruction emerging as fundamental tasks. Although some works attempt to couple these tasks, they primarily focus on cascade learning while neglecting task associativity within a broader parameter space, leading to suboptimal performance. This work introduces a novel approach by rethinking denoising and reconstruction from a "backbone-head" perspective, leveraging the stronger shared parameter space offered by the backbone, compared to the encoder used in existing works. We derive task-specific heads with fewer parameters to mitigate learning pressure. By incorporating chromaticity-and-noise perception module into the backbone and introducing task-specific supervision during training, we enable simultaneous high-quality results for reconstruction and denoising. Additionally, we design a dual-head interaction module to capture the latent correspondence between the two tasks, significantly enhancing multi-task accuracy. Extensive experiments validate the superiority of the proposed method. Code is available at: https://github.com/csmty/CANS.

Video-Text Retrieval (VTR) is a core task in multi-modal understanding, drawing growing attention from both academia and industry in recent years. While numerous VTR methods have achieved success, most of them assume accurate visual-text correspondences during training, which is difficult to ensure in practice due to ubiquitous noise, known as noisy correspondences (NC). In this paper, we rethink how to mitigate the NC from the perspective of representative reference features (termed agents), and propose a novel relation-aware purified consistency (RPC) network to amend direct pairwise correlation, including representative agents construction and relation-aware ranking distribution alignment. The proposed RPC enjoys several merits. First, to learn the agents well without any correspondence supervision, we customize the agents construction according to the three characteristics of reliability, representativeness, and resilience. Second, the ranking distribution-based alignment process leverages the structural information inherent in inter-pair relationships, making it more robust compared to individual comparisons. Extensive experiments on five datasets under different settings demonstrate the efficacy and robustness of our method.

Monocular 3D lane detection is a fundamental task in autonomous driving. Although sparse-point methods lower computational load and maintain high accuracy in complex lane geometries, current methods fail to fully leverage the geometric structure of lanes in both lane geometry representations and model design. In lane geometry representations, we present a theoretical analysis alongside experimental validation to verify that current sparse lane representation methods contain inherent flaws, resulting in potential errors of up to 20 m, which raise significant safety concerns for driving. To address this issue, we propose a novel patching strategy to completely represent the full lane structure. To enable existing models to match this strategy, we introduce the EndPoint head (EP-head), which adds a patching distance to endpoints. The EP-head enables the model to predict more complete lane representations even with fewer preset points, effectively addressing existing limitations and paving the way for models that are faster and require fewer parameters in the future. In model design, to enhance the model's perception of lane structures, we propose the PointLane attention (PL-attention), which incorporates prior geometric knowledge into the attention mechanism. Extensive experiments demonstrate the effectiveness of the proposed methods on various state-of-the-art models. For instance, in terms of the overall F1-score, our methods improve Persformer by 4.4 points, Anchor3DLane by 3.2 points, and LATR by 2.8 points. The code will be available soon.

Contrastive language-image pretraining models such as CLIP have demonstrated remarkable performance in various text-image alignment tasks. However, the inherent 77-token input limitation and reliance on predominantly short-text training data restrict its ability to handle long-text tasks effectively. To overcome these constraints, we propose LongD-CLIP, a dual-teacher distillation framework designed to enhance long-text representation while mitigating knowledge forgetting. In our approach, a teacher model, fine-tuned on long-text data, distills rich representation knowledge into a student model, while the original CLIP serves as a secondary teacher to help the student retain its foundational knowledge. Extensive experiments reveal that LongD-CLIP significantly outperforms existing models across long-text retrieval, short-text retrieval, and zero-shot image classification tasks. For instance, in the image-to-text retrieval task on the ShareGPT4V test set, LongD-CLIP exceeds Long-CLIP's performance by 2.5%, achieving an accuracy of 98.3%. Similarly, on the Urban-1k dataset, it records a 9.2% improvement, reaching 91.9%, thereby underscoring its robust generalization capabilities. Additionally, the text encoder of LongD-CLIP exhibits reduced latent space drift and improved compatibility with existing generative models, effectively overcoming the 77-token input constraint.

In text-to-image (T2I) generation applications, negative embeddings have proven to be a simple yet effective approach for enhancing generation quality. Typically, these negative embeddings are derived from user-defined negative prompts, which, while being functional, are not necessarily optimal. In this paper, we introduce ReNeg, an end-to-end method designed to learn improved Negative embeddings guided by a Reward model. We employ a reward feedback learning framework and integrate classifier-free guidance (CFG) into the training process, which was previously utilized only during inference, thus enabling the effective learning of negative embeddings. We also propose two strategies for learning both global and per-sample negative embeddings. Extensive experiments show that the learned negative embedding significantly outperforms null-text and handcrafted counterparts, achieving substantial improvements in human preference alignment. Additionally, the negative embedding learned within the same text embedding space exhibits strong generalization capabilities. For example, using the same CLIP text encoder, the negative embedding learned on SD1.5 can be seamlessly transferred to text-to-image or even text-to-video models such as ControlNet, ZeroScope, and VideCrafter2, resulting in consistent performance improvements across the board. Code is available at https://github.com/AMD-AIG-AIMA/ReNeg.

Rotated object detection has made significant progress in the optical remote sensing. However, advancements in the Synthetic Aperture Radar (SAR) field are laggard behind, primarily due to the absence of a large-scale dataset. Annotating such a dataset is inefficient and costly. A promising solution is to employ a weakly supervised model (e.g., trained with available horizontal boxes only) to generate pseudo-rotated boxes for reference before manual calibration. Unfortunately, the existing weakly supervised models exhibit limited accuracy in predicting the object's angle. Previous works attempt to enhance angle prediction by using angle resolvers that decouple angles into cosine and sine encodings. In this work, we first reevaluate these resolvers from a unified perspective of dimension mapping and expose that they share the same shortcomings: these methods overlook the unit cycle constraint inherent in these encodings, easily leading to prediction biases. To address this issue, we propose the Unit Cycle Resolver (UCR), which incorporates a unit circle constraint loss to improve angle prediction accuracy. Our approach can effectively improve the performance of existing state-of-the-art weakly supervised methods and even surpasses fully supervised models on existing optical benchmarks (i.e., DOTA-v1.0). With the aid of UCR, we further annotate and introduce RSAR, the largest multi-class rotated SAR object detection dataset to date. Extensive experiments on both RSAR and optical datasets demonstrate that our UCR enhances angle prediction accuracy.

There is growing interest in solving computer vision problems such as mesh or point set alignment using Adiabatic Quantum Computing (AQC). Unfortunately, modern experimental AQC devices such as D-Wave only support Quadratic Unconstrained Binary Optimisation (QUBO) problems, which severely limits their applicability. This paper proposes a new way to overcome this limitation and introduces QuCOOP, an optimisation framework extending the scope of AQC to composite and binary-parametrised, possibly non-quadratic problems. The key idea of QuCOOP is to iteratively approximate the original objective function by a sequel of local (intermediate) QUBO forms, whose binary parameters can be sampled on AQC devices. We experiment with quadratic assignment problems, shape matching and point set registration without knowing the correspondences in advance. Our approach achieves state-of-the-art results across multiple instances of tested problems.