CVPR 2025 论文列表

Masked video modeling, such as VideoMAE, is an effective paradigm for video self-supervised learning (SSL). However, they are primarily based on reconstructing pixel level details on natural videos which have substantial temporal redundancy, limiting their capability for semantic representation and sufficient encoding of motion dynamics. To address these issues, this paper introduces a novel SSL approach for video representation learning, dubbed as SMILE, by infusing both spatial and motion semantics. In SMILE, we leverage image-language pretrained models, such as CLIP, to guide the learning process with their high-level spatial semantics. We enhance the representation of motion by introducing synthetic motion patterns in the training data, allowing the model to capture more complex and dynamic content. Furthermore, using SMILE, we establish a new self-supervised video learning paradigm capable of learning strong video representations without requiring any natural video data. We have carried out extensive experiments on 7 datasets with various downstream scenarios. SMILE surpasses current state-of-the-art SSL methods, showcasing its effectiveness in learning more discriminative and generalizable video representations.

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 Vision-Language Models (LVLMs) have emerged as transformative tools in multimodal tasks, seamlessly integrating pretrained vision encoders to align visual and textual modalities. Prior works have highlighted the susceptibility of LVLMs to dual exploits (gradient-based and optimization-based jailbreak attacks), which leverage the expanded attack surface introduced by the image modality. Despite advancements in enhancing robustness, existing methods fall short in their ability to defend against dual exploits while preserving fine-grained semantic details and overall semantic coherence under intense adversarial perturbations. To bridge this gap, we introduce SheiLding against Dual Exploits (SLADE), a novel unsupervised adversarial fine-tuning scheme that enhances the resilience of CLIP-based vision encoders. SLADE's dual-level contrastive learning approach balances the granular and the holistic, capturing fine-grained image details without losing sight of high-level semantic coherence. Extensive experiments demonstrate that SLADE-equipped LVLMs set a new benchmark for robustness against dual exploits while preserving fine-grained semantic details of perturbed images. Notably, SLADE achieves these results without compromising the core functionalities of LVLMs, such as instruction following, or requiring the computational overhead (e.g., large batch sizes, momentum encoders) commonly associated with traditional contrastive learning methods.

Generating layouts from textual descriptions by large language models (LLMs) plays a crucial role in precise spatial reasoning-induced domains such as robotic object rearrangement and text-to-image generation. However, current methods face challenges in limited real-world examples, handling diverse layout descriptions and varying levels of granularity. To address these issues, a novel framework named Spatial Knowledge Enhanced Layout (SKE-Layout), is introduced. SKE-Layout integrates mixed spatial knowledge sources, leveraging both real and synthetic data to enhance spatial contexts. It utilizes diverse representations tailored to specific tasks and employs contrastive learning and multitask learning techniques for accurate spatial knowledge retrieval. This framework generates more accurate and fine-grained visual layouts for object rearrangement and text-to-image generation tasks, achieving improvements of 5%-30% compared to existing methods.

The computer vision community has developed numerous techniques for digitally restoring true scene information from single-view degraded photographs, an important yet extremely ill-posed task. In this work, we tackle image restoration from a different perspective by jointly denoising multiple photographs of the same scene. Our core hypothesis is that degraded images capturing a shared scene contain complementary information that, when combined, better constrains the restoration problem. To this end, we implement a powerful multi-view diffusion model that jointly generates uncorrupted views by extracting rich information from multi-view relationships. Our experiments show that our multi-view approach outperforms existing single-view image and even video-based methods on image deblurring and super-resolution tasks. Critically, our model is trained to output 3D consistent images, making it a promising tool for applications requiring robust multi-view integration, such as 3D reconstruction or pose estimation.

Implicit Neural Representations (INRs) are increasingly recognized as a versatile data modality for representing discretized signals, offering benefits such as infinite query resolution and reduced storage requirements. Existing signal compression approaches for INRs typically employ one of two strategies: 1. direct quantization with entropy coding of the trained INR; 2. deriving a latent code on top of the INR through a learnable transformation. Thus, their performance is heavily dependent on the quantization and entropy coding schemes employed. In this paper, we introduce SINR, an innovative compression algorithm that leverages the patterns in the vector spaces formed by weights of INRs. We compress these vector spaces using a high-dimensional sparse code within a dictionary. Further analysis reveals that the atoms of the dictionary used to generate the sparse code do not need to be learned or transmitted to successfully recover the INR weights. We demonstrate that the proposed approach can be integrated with any existing INR-based signal compression technique. Our results indicate that SINR achieves substantial reductions in storage requirements for INRs across various configurations, outperforming conventional INR-based compression baselines. Furthermore, SINR maintains high-quality decoding across diverse data modalities, including images, occupancy fields, and Neural Radiance Fields.

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.

The rapid advancement of generative models in creating highly realistic images poses substantial risks for misinformation dissemination. For instance, a synthetic image, when shared on social media, can mislead extensive audiences and erode trust in digital content, resulting in severe repercussions. Despite some progress, academia has not yet created a large and diversified deepfake detection dataset for social media, nor has it devised an effective solution to address this issue. In this paper, we introduce the Social media Image Detection dataSet (SID-Set), which offers three key advantages: (1) extensive volume, featuring 300K AI-generated/tampered and authentic images with comprehensive annotations, (2) broad diversity, encompassing fully synthetic and tampered images across various classes, and (3) elevated realism, with images that are predominantly indistinguishable from genuine ones through mere visual inspection. Furthermore, leveraging the exceptional capabilities of large multimodal models, we propose a new image deepfake detection, localization, and explanation framework, named SIDA (Social media Image Detection, localization, and explanation Assistant). SIDA not only discerns the authenticity of images, but also delineates tampered regions through mask prediction and provides textual explanations of the model's judgment criteria. Compared with state-of-the-art deepfake detection models on SID-Set and other benchmarks, extensive experiments demonstrate that SIDA achieves superior performance among diversified settings. The code, model, and dataset will be released.

Applying style transfer to a full 3D environment is a challenging task that has seen many developments since the advent of neural rendering. 3D Gaussian splatting (3DGS) has recently pushed further many limits of neural rendering in terms of training speed and reconstruction quality. This work introduces SGSST: Scaling Gaussian Splatting Style Transfer, an optimization-based method to apply style transfer to pretrained 3DGS scenes. We demonstrate that a new multiscale loss based on global neural statistics, that we name SOS for Simultaneously Optimized Scales, enables style transfer to ultra-high resolution 3D scenes. Not only SGSST pioneers 3D scene style transfer at such high image resolutions, it also produces superior visual quality as assessed by thorough qualitative, quantitative and perceptual comparisons.

Recently, camera-based solutions have been extensively explored for scene semantic completion (SSC). Despite their success in visible areas, existing methods struggle to capture complete scene semantics due to frequent visual occlusions. To address this limitation, this paper presents the first satellite-ground cooperative SSC framework, i.e., SGFormer, exploring the potential of satellite-ground image pairs in the SSC task. Specifically, we propose a dual-branch architecture that encodes orthogonal satellite and ground views in parallel, unifying them into a common domain. Additionally, we design a ground-view guidance strategy that pre-corrects satellite image biases during feature encoding, addressing misalignment between satellite and ground views. Moreover, we develop an adaptive weighting strategy that balances contributions from satellite and ground views. Experiments demonstrate that SGFormer outperforms the state of the art on SemanticKITTI and SSCBench-KITTI-360 datasets. Our code is available on https://github.com/gxytcrc/SGFormer.

Neural rendering techniques have made substantial progress in generating photo-realistic 3D scenes. The latest 3D Gaussian Splatting technique has achieved high quality novel view synthesis as well as fast rendering speed. However, 3D Gaussians lack proficiency in defining accurate 3D geometric structures despite their explicit primitive representations. This is due to the fact that Gaussian's attributes are primarily tailored and fine-tuned for rendering diverse 2D images by their anisotropic nature. To pave the way for efficient 3D reconstruction, we present Spherical Gaussians, a simple and effective representation for 3D geometric boundaries, from which we can directly reconstruct 3D feature curves from a set of calibrated multi-view images. Spherical Gaussians is optimized from grid initialization with a view-based rendering loss, where a 2D edge map is rendered at a specific view and then compared to the ground-truth edge map extracted from the corresponding image, without the need for any 3D guidance or supervision. Given Spherical Gaussians serve as intermedia for the robust edge representation, we further introduce a novel optimization-based algorithm called SGCR to directly extract accurate parametric curves from aligned Spherical Gaussians. We demonstrate that SGCR outperforms existing state-of-the-art methods in 3D edge reconstruction while enjoying great efficiency.

Recent open-vocabulary human-object interaction (OV-HOI) detection methods primarily rely on large language model (LLM) for generating auxiliary descriptions and leverage knowledge distilled from CLIP to detect unseen interaction categories. Despite their effectiveness, these methods face two challenges: (1) feature granularity deficiency, due to reliance on last layer visual features for text alignment, leading to the neglect of crucial object-level details from intermediate layers; (2) semantic similarity confusion, resulting from CLIP's inherent biases toward certain classes, while LLM-generated descriptions based solely on labels fail to adequately capture inter-class similarities. To address these challenges, we propose a stratified granular comparison network. First, we introduce a granularity sensing alignment module that aggregates global semantic features with local details, refining interaction representations and ensuring robust alignment between intermediate visual features and text embeddings. Second, we develop a hierarchical group comparison module that recursively compares and groups classes using LLMs, generating fine-grained and discriminative descriptions for each interaction category. Experimental results on two widely-used benchmark datasets, SWIG-HOI and HICO-DET, demonstrate that our method achieves state-of-the-art results in OV-HOI detection. Codes is available at https://github.com/Phil0212/SGC-Net.

In this study, we introduce a novel two-stage technique for decomposing and reconstructing facial features from sparse-view images, a task made challenging by the unique geometry and complex skin reflectance of each individual. To synthesize 3D facial models more realistically, we endeavor to decouple key facial attributes from the RGB color, including geometry, diffuse reflectance, and specular reflectance. Specifically, we design a Sparse-view Face Decomposition Model (SFDM): 1) In the first stage, we create a general facial template from a wide array of individual faces, encapsulating essential geometric and reflectance characteristics. 2) Guided by this template, we refine a specific facial model for each individual in the second stage, considering the interaction between geometry and reflectance, as well as the effects of subsurface scattering on the skin. With these advances, our method can reconstruct high-quality facial representations from as few as three images. The comprehensive evaluation and comparison reveal that our approach outperforms existing methods by effectively disentangling geometric and reflectance components, significantly enhancing the quality of synthesized novel views, and paving the way for applications in facial relighting and reflectance editing.

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

Video-based Large Language Models (Video-LLMs) have witnessed substantial advancements in recent years, propelled by the advancement in multi-modal LLMs. Although these models have demonstrated proficiency in providing the overall description of videos, they struggle with fine-grained understanding, particularly in aspects such as visual dynamics and video details inquiries. To tackle these shortcomings, we find that fine-tuning Video-LLMs on self-supervised fragment tasks, greatly improve their fine-grained video understanding abilities. Hence we propose two key contributions:(1) Self-Supervised Fragment Fine-Tuning (SF^2T), a novel effortless fine-tuning method, employs the rich inherent characteristics of videos for training, while unlocking more fine-grained understanding ability of Video-LLMs. Moreover, it relieves researchers from labor-intensive annotations and smartly circumvents the limitations of natural language, which often fails to capture the complex spatiotemporal variations in videos;(2) A novel benchmark dataset, namely FineVidBench, for rigorously assessing Video-LLMs' performance at both the scene and fragment levels, offering a comprehensive evaluation of their capabilities.We assessed multiple models and validated the effectiveness of SF^2T on them. Experimental results reveal that our approach improves their ability to capture and interpret spatiotemporal details.

Deep learning has significantly advanced the object detection field. However, tiny object detection (TOD) remains a challenging problem. We provide a new analysis method to examine the TOD challenge through occlusion-based attribution analysis in the frequency domain. We observe that tiny objects become less distinct after feature encoding and can benefit from the removal of high-frequency information. In this paper, we propose a novel approach named Spectral Enhancement for Tiny object detection (SET), which amplifies the frequency signatures of tiny objects in a heterogeneous architecture. SET includes two modules. The Hierarchical Background Smoothing (HBS) module suppresses high-frequency noise in the background through adaptive smoothing operations. The Adversarial Perturbation Injection (API) module leverages adversarial perturbations to increase feature saliency in critical regions and prompt the refinement of object features during training. Extensive experiments on four datasets demonstrate the effectiveness of our method. Especially, SET boosts the prior art RFLA by 3.2% AP on the AI-TOD dataset.

Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. Traditional works focus on aligning visual features between domains to extract domain-invariant knowledge, and recent VLM-based DAOD methods leverage semantic information provided by the textual encoder to supplement domain-specific features for each domain.However, they overlook the role of semantic information in guiding the learning of visual features that are beneficial for adaptation.To solve the problem, we propose semantic entropy to quantify the semantic information contained in visual features, and design SEmantic ENtropy guided Domain-aware Attention (SEEN-DA) to adaptively refine visual features with the semantic information of two domains.Semantic entropy reflects the importance of features based on semantic information, which can serve as attention to select discriminative visual features and suppress semantically irrelevant redundant information.Guided by semantic entropy, we introduce domain-aware attention modules into the visual encoder in SEEN-DA.It utilizes an inter-domain attention branch to extract domain-invariant features and eliminate redundant information, and an intra-domain attention branch to supplement the domain-specific semantic information discriminative on each domain.Comprehensive experiments validate the effectiveness of SEEN-DA, demonstrating significant improvements in cross-domain object detection performance.

Few-shot class-incremental learning (FSCIL) presents a significant challenge in machine learning, requiring models to integrate new classes from limited examples while preserving performance on previously learned classes. Recently, prompt-based CIL approaches leverage ample data to train prompts, effectively mitigating catastrophic forgetting. However, these methods do not account for the semantic features embedded in prompts, exacerbating the plasticity-stability dilemma in few-shot incremental learning. In this paper, we propose a novel and simple framework named SEmantic Complementary Prompt(SEC-Prompt), which learns two sets of semantically complementary prompts based on an adaptive query: discriminative prompts(D-Prompt) and non-discriminative prompts(ND-Prompt). D-Prompt enhances the separation of class-specific feature distributions by strengthening key discriminative features, while ND-Prompt balances non-discriminative information to promote generalization to novel classes. To efficiently learn high-quality knowledge from limited samples, we leverage ND-Prompt for data augmentation to increase sample diversity and introduce Prompt Clustering Loss to prevent noise contamination in D-Prompt, ensuring robust discriminative feature learning and improved generalization. Our experimental results showcase state-of-the-art performance across three benchmark datasets, including CIFAR100, ImageNet-R and CUB datasets.

Long video understanding presents challenges due to the inherent high computational complexity and redundant temporal information. An effective representation for long videos must efficiently process such redundancy while preserving essential contents for downstream tasks. This paper introduces **SE**mantic **A**ttention **L**earning (SEAL), a novel unified representation for long videos. To reduce computational complexity, long videos are decomposed into three distinct types of semantic entities: scenes, objects, and actions, allowing models to operate on a compact set of entities rather than a large number of frames or pixels. To further address redundancy, we propose an attention learning module that balances token relevance with diversity, formulated as a subset selection optimization problem. Our representation is versatile, enabling applications across various long video understanding tasks. Our representation is versatile and applicable across various long video understanding tasks. Extensive experiments demonstrate that SEAL significantly outperforms state-of-the-art methods in video question answering and temporal grounding tasks across diverse benchmarks, including LVBench, MovieChat-1K, and Ego4D.