CVPR 2025 Papers

Referring video object segmentation (RVOS) seeks to segment the objects within a video referred by linguistic expressions. Existing RVOS solutions follow a "fuse then select" paradigm: establishing semantic correlation between visual and linguistic feature, and performing frame-level query interaction to select the instance mask per frame with instance segmentation module. This paradigm overlooks the challenge of semantic gap between the linguistic descriptor and the video object as well as the underlying clutters in the video. This paper proposes a novel Semantic and Sequential Alignment (SSA) paradigm to handle these challenges. We first insert a lightweight adapter after the vision language model (VLM) to perform the semantic alignment. Then, prior to selecting mask per frame, we exploit the trajectory-to-instance enhancement for each frame via sequential alignment. This paradigm leverages the visual-language alignment inherent in VLM during adaptation and tries to capture global information by ensembling trajectories. This helps understand videos and the corresponding descriptors by mitigating the discrepancy with intricate activity semantics, particularly when facing occlusion or similar interference. SSA demonstrates competitive performance while maintaining fewer learnable parameters.

Most vision-language models today are primarily trained on English image-text pairs, with non-English pairs often filtered out. Evidence from cross-cultural psychology suggests that this approach will bias models against perceptual modes exhibited by people who speak other (non-English) languages. We investigate semantic and expressive variation in image captions across different languages; we analyze both human-annotated datasets and model-produced captions. By analyzing captions across seven languages (English, French, German, Russian, Chinese, Japanese, Korean) in high-quality image captioning datasets (Crossmodal and Visual Genome), we find that multilingual caption sets tend to provide richer visual descriptions than monolingual (including English-only) ones; multilingual sets contain 46.0% more objects, 66.1% more relationships, and 66.8% more attributes. We observe the same results with multilingual captions produced by LLaVA and the Google Vertex API: for example, compared to monolingual captions, they cover 21.9% more objects,18.8% more relations, and 20.1% more attributes. These suggest that, across a large number of samples, different languages bias people and models to focus on different visual concepts. Finally, we show that models trained on image-text data in one language perform distinctly better on that language's test set. Our work points towards the potential value of training vision models on multilingual data sources to widen the range/variation of descriptive information those models are exposed to.

Open-vocabulary semantic segmentation models associate vision and text to label pixels from an undefined set of classes using textual queries, providing versatile performance on novel datasets. However, large shifts between training and test domains degrade their performance, requiring fine-tuning for effective real-world applications. We introduce Semantic Library Adaptation (SemLA), a novel framework for training-free, test-time domain adaptation. SemLA leverages a library of LoRA-based adapters indexed with CLIP embeddings, dynamically merging the most relevant adapters based on proximity to the target domain in the embedding space. This approach constructs an ad-hoc model tailored to each specific input without additional training. Our method scales efficiently, enhances explainability by tracking adapter contributions, and inherently protects data privacy, making it ideal for sensitive applications. Comprehensive experiments on a 20-domain benchmark built over 10 standard datasets demonstrate SemLA's superior adaptability and performance across diverse settings, establishing a new standard in domain adaptation for open-vocabulary semantic segmentation.

Generating reasonable and high-quality human interactive motions in a given dynamic environment is crucial for understanding, modeling, transferring, and applying human behaviors to both virtual and physical robots. In this paper, we introduce an effective method, SemGeoMo, for dynamic contextual human motion generation, which fully leverages the text-affordance-joint multi-level semantic and geometric guidance in the generation process, improving the semantic rationality and geometric correctness of generative motions. Our method achieves state-of-the-art performance on three datasets and demonstrates superior generalization capability for diverse interaction scenarios.

Semantic correspondence made tremendous progress through the recent advancements of large vision models (LVM). While these LVMs have been shown to reliably capture local semantics, the same can currently not be said for capturing global geometric relationships between semantic object regions. This problem leads to unreliable performance for semantic correspondence between images with extreme view variation. In this work, we aim to leverage monocular depth estimates to capture these geometric relationships for more robust and data-efficient semantic correspondence. First, we introduce a simple but effective method to build 3D object-class representations from monocular depth estimates and LVM features using a sparsely annotated image correspondence dataset. Second, we formulate an alignment energy that can be minimized using gradient descent to obtain an alignment between the 3D object-class representation and the object-class instance in the input RGB-image. Our method achieves state-of-the-art matching accuracy in multiple categories on the challenging SPair-71k dataset, increasing the PCK@0.1 score by more than 10 points on three categories and overall by 3.3 points from 85.6% to 88.9%. Additional resources and code are available at dub.sh/semalign3d.

We propose SelfSplat, a novel 3D Gaussian Splatting model designed to perform pose-free and 3D prior-free generalizable 3D reconstruction from unposed multi-view images. These settings are inherently ill-posed due to the lack of ground-truth data, learned geometric information, and the need to achieve accurate 3D reconstruction without finetuning, making it difficult for conventional methods to achieve high-quality results. Our model addresses these challenges by effectively integrating explicit 3D representations with self-supervised depth and pose estimation techniques, resulting in reciprocal improvements in both pose accuracy and 3D reconstruction quality. Furthermore, we incorporate a matching-aware pose estimation network and a depth refinement module to enhance geometry consistency across views, ensuring more accurate and stable 3D reconstructions. To present the performance of our method, we evaluated it on large-scale real-world datasets, including RealEstate10K, ACID, and DL3DV. SelfSplat achieves superior results over previous state-of-the-art methods in both appearance and geometry quality, also demonstrates strong cross-dataset generalization capabilities. Extensive ablation studies and analysis also validate the effectiveness of our proposed methods.

Existing diffusion-based video super-resolution (VSR) methods are susceptible to introducing complex degradations and noticeable artifacts into high-resolution videos due to their inherent randomness. In this paper, we propose a noise-robust real-world VSR framework by incorporating self-supervised learning and Mamba into pre-trained latent diffusion models. To ensure content consistency across adjacent frames, we enhance the diffusion model with a global spatio-temporal attention mechanism using the Video State-Space block with a 3D Selective Scan module, which reinforces coherence at an affordable computational cost. To further reduce artifacts in generated details, we introduce a self-supervised ControlNet that leverages HR features as guidance and employs contrastive learning to extract degradation-insensitive features from LR videos. Finally, a three-stage training strategy based on a mixture of HR-LR videos is proposed to stabilize VSR training. The proposed Self-supervised ControlNet with Spatio-Temporal Continuous Mamba based VSR algorithm achieves superior perceptual quality than state-of-the-arts on real-world VSR benchmark datasets, validating the effectiveness of the proposed model design and training strategies.

We present a method for finding cross-modal space-time correspondences. Given two images from different visual modalities, such as an RGB image and a depth map, our model identifies which pairs of pixels correspond to the same physical points in the scene. To solve this problem, we extend the contrastive random walk framework to simultaneously learn cycle-consistent feature representations for both cross-modal and intra-modal matching. The resulting model is simple and has no explicit photo-consistency assumptions. It can be trained entirely using unlabeled data, without the need for any spatially aligned multimodal image pairs. We evaluate our method on both geometric and semantic correspondence tasks. For geometric matching, we consider challenging tasks such as RGB-to-depth and RGB-to-thermal matching (and vice versa); for semantic matching, we evaluate on photo-sketch and cross-style image alignment. Our method achieves strong performance across all benchmarks.

Spike camera is a kind of neuromorphic camera with ultra-high temporal resolution, which can capture dynamic scenes by continuously firing spike signals. To capture color information, a color filter array (CFA) is employed on the sensor of the spike camera, resulting in Bayer-pattern spike streams. How to restore high-quality color images from the binary spike signals remains challenging. In this paper, we propose a motion-guided reconstruction method for spike cameras with CFA, utilizing color layout and estimated motion information. Specifically, we develop a joint motion estimation pipeline for the Bayer-pattern spike stream, exploiting the motion consistency of channels. We propose to estimate the missing pixels of each color channel according to temporally neighboring pixels of the corresponding color along the motion trajectory. As the spike signals are read out at discrete time points, there is quantization noise that impacts the image quality. Thus, we analyze the correlation of the noise in spatial and temporal domains and propose a self-supervised network utilizing a masked spike encoder to handle the noise. Experiments on real-world captured Bayer-pattern spike streams show that our method can restore color images with better visual quality, compared with state-of-the-art methods. The source codes are available at https://github.com/csycdong/SSL-CSC.

Point cloud completion helps restore partial incomplete point clouds suffering occlusions. Current self-supervised methods fail to give high fidelity completion for large objects with missing surfaces and unbalanced distribution of available points. In this paper, we present a novel method for restoring large-scale point clouds with limited and imbalanced ground-truth. Using rough boundary annotations for a region of interest, we project the original point clouds into a multiple-center-of-projection (MCOP) image, where fragments are projected to images of 5 channels (RGB, depth, and rotation). Completion of the original point cloud is reduced to inpainting the missing pixels in the MCOP images. Due to lack of complete structures and an unbalanced distribution of existing parts, we develop a self-supervised scheme which learns to infill the MCOP image with points resembling existing "complete" patches. Special losses are applied to further enhance the regularity and consistency of completed MCOP images, which is mapped back to 3D to form final restoration. Extensive experiments demonstrate the superiority of our method in completing 600+ incomplete and unbalanced archaeological structures in Peru.

Learning self-supervised visual correspondence is a long-studied task fundamental to visual understanding and human perception. However, existing correspondence methods largely focus on small image transformations, such as object tracking in high-framerate videos or learning pixel-to-pixel mappings between images with high view overlap. This severely limits their application in dynamic multi-view settings such as robot imitation learning. In this work, we introduce Predictive Cycle Consistency for learning object correspondence between extremely disjoint views of a scene without paired segmentation data. Our technique bootstraps object correspondence pseudolabels from raw image segmentations using conditional grayscale colorization and a cycle-consistency refinement prior. We then train deep ViTs on these pseudolabels, which we use to generate higher-quality pseudolabels and iteratively train better correspondence models. We demonstrate the performance of our method under both extreme in-the-wild camera view changes and across large temporal gaps in video. Our approach beats all prior supervised and prior SoTA self-supervised correspondence models on the EgoExo4D correspondence benchmark (+6.7 IoU Exo Query) and the prior SoTA self-supervised methods SiamMAE and DINO V1&V2 on the DAVIS-2017 and LVOS datasets across large frame gaps.

Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between stability and adaptability. Relying on the generalizable representation in pre-trained models (PTMs), PTM-based CL methods perform effective continual adaptation on downstream tasks by adding learnable adapters or prompts upon the frozen PTMs. However, many existing PTM-based CL methods use restricted adaptation on a fixed set of these modules to avoid forgetting, suffering from limited CL ability. Periodically adding task-specific modules results in linear model growth rate and impaired knowledge reuse. We propose Self-Expansion of pre-trained models with Modularized Adaptation (SEMA), a novel approach to enhance the control of stability-plasticity balance in PTM-based CL. SEMA automatically decides to reuse or add adapter modules on demand in CL, depending on whether significant distribution shift that cannot be handled is detected at different representation levels. We design modular adapter consisting of a functional adapter and a representation descriptor. The representation descriptors are trained as a distribution shift indicator and used to trigger self-expansion signals. For better composing the adapters, an expandable weighting router is learned jointly for mixture of adapter outputs. SEMA enables better knowledge reuse and sub-linear expansion rate. Extensive experiments demonstrate the effectiveness of the proposed self-expansion method, achieving state-of-the-art performance compared to PTM-based CL methods without memory rehearsal. Code is available at https://github.com/huiyiwang01/SEMA-CL.

We study the problem of building a visual concept library for visual recognition. Building effective visual concept libraries is challenging, as manual definition is labor-intensive, while relying solely on LLMs for concept generation can result in concepts that lack discriminative power or fail to account for the complex interactions between them. Our approach, ESCHER, takes a library learning perspective to iteratively discover and improve visual concepts. ESCHER uses a vision-language model (VLM) as a critic to iteratively refine the concept library, including accounting for interactions between concepts and how they affect downstream classifiers. By leveraging the in-context learning abilities of LLMs and the history of performance using various concepts, ESCHER dynamically improves its concept generation strategy based on the VLM critic's feedback. Finally, ESCHER does not require any human annotations, and is thus an automated plug-and-play framework. We empirically demonstrate the ability of ESCHER to learn a concept library for zero-shot, few-shot, and fine-tuning visual classification tasks. This work represents, to our knowledge, the first application of concept library learning to real-world visual tasks.

Diffusion models achieved unprecedented fidelity and diversity for synthesizing image, video, 3D assets, etc. However, subject mixing is an unresolved issue for diffusion-based image synthesis, particularly for synthesizing multiple similar-looking subjects. We propose Self-Cross Diffusion Guidance to penalize the overlap between cross-attention maps and the aggregated self-attention map. Compared to previous methods based on self-attention or cross-attention alone, our guidance is more effective in eliminating subject mixing. What's more, our guidance addresses subject mixing for all relevant patches beyond the most discriminant one, e.g., the beak of a bird. For each subject, we aggregate self-attention maps of patches with higher cross-attention values. Thus, the aggregated self-attention map forms a region that the whole subject attends to. Our training-free method boosts the performance of both Unet-based and Transformer-based diffusion models such as the Stable Diffusion series. We also release a similar subjects dataset (SSD), a challenging benchmark, and utilize GPT-4o for automatic and reliable evaluation. Extensive qualitative and quantitative results demonstrate the effectiveness of our self-cross diffusion guidance.

Cone-beam computed tomography (CBCT) is a standard imaging modality in orofacial and dental practices, providing essential 3D volumetric imaging of anatomical structures, including jawbones, teeth, sinuses, and neurovascular canals. Accurately segmenting these structures is fundamental to numerous clinical applications, such as surgical planning and implant placement. However, manual segmentation of CBCT scans is time-intensive and requires expert input, creating a demand for automated solutions through deep learning. Effective development of such algorithms relies on access to large, well-annotated datasets, yet current datasets are often privately stored or limited in scope and considered structures, especially concerning 3D annotations. This paper proposes ToothFairy2, a comprehensive, publicly accessible CBCT dataset with voxel-level 3D annotations of 42 distinct classes corresponding to maxillofacial structures. We validate the dataset by benchmarking state-of-the-art neural network models, including convolutional, transformer-based, and hybrid Mamba-based architectures, to evaluate segmentation performance across complex anatomical regions. Our work also explores adaptations to the nnU-Net framework to optimize multi-class segmentation for maxillofacial anatomy. The proposed dataset provides a fundamental resource for advancing maxillofacial segmentation and supports future research in automated 3D image analysis in digital dentistry.

This paper presents Segment This Thing (STT), a new efficient image segmentation model designed to produce a single segment given a single point prompt. Instead of following prior work and increasing efficiency by decreasing model size, we gain efficiency by foveating input images. Given an image and a point prompt, we extract a crop centered on the prompt and apply a novel variable-resolution patch tokenization in which patches are downsampled at a rate that increases with increased distance from the prompt. This approach yields far fewer image tokens than uniform patch tokenization. As a result we can drastically reduce the computational cost of segmentation without reducing model size. Furthermore, the foveation focuses the model on the region of interest, a potentially useful inductive bias. We show that our Segment This Thing model is more efficient than prior work while remaining competitive on segmentation benchmarks. It can easily run at interactive frame rates on consumer hardware and is thus a promising tool for augmented reality or robotics applications.

Amodal instance segmentation, which aims to detect and segment both visible and invisible parts of objects in images, plays a crucial role in various applications, including autonomous driving, robotic manipulation, and scene understanding. While existing methods require training both front-end detectors and mask decoders jointly, this approach lacks flexibility and fails to leverage the strengths of pre-existing modal detectors. To address this limitation, we propose SAMEO, a novel framework that adapts the Segment Anything Model (SAM) as a versatile mask decoder capable of interfacing with various front-end detectors to enable mask prediction even for partially occluded objects. Acknowledging the constraints of limited amodal segmentation datasets, we introduce Amodal-LVIS, a large-scale synthetic dataset comprising 300K images derived from the modal LVIS and LVVIS datasets. This dataset significantly expands the training data available for amodal segmentation research. Our experimental results demonstrate that our approach, when trained on the newly extended dataset, including Amodal-LVIS, achieves remarkable zero-shot performance on both COCOA-cls and D2SA benchmarks, highlighting its potential for generalization to unseen scenarios.

Despite their success, Segment Anything Models (SAMs) experience significant performance drops on severely degraded, low-quality images, limiting their effectiveness in real-world scenarios. To address this, we propose GleSAM, which utilizes Generative Latent space Enhancement to boost robustness on low-quality images, thus enabling generalization across various image qualities. Specifically, we adapt the concept of latent diffusion to SAM-based segmentation frameworks and perform the generative diffusion process in the latent space of SAM to reconstruct high-quality representation, thereby improving segmentation. Additionally, we introduce two techniques to improve compatibility between the pre-trained diffusion model and the segmentation framework. Our method can be applied to pre-trained SAM and SAM2 with only minimal additional learnable parameters, allowing for efficient optimization. We also construct the LQSeg dataset with a greater diversity of degradation types and levels for training and evaluating the model. Extensive experiments demonstrate that GleSAM significantly improves segmentation robustness on complex degradations while maintaining generalization to clear images. Furthermore, GleSAM also performs well on unseen degradations, underscoring the versatility of our approach and dataset. Codes and datasets will be available soon.