CVPR 2025 论文列表

In this work, we study Weakly Supervised Spatio-Temporal Video Grounding (WSTVG), a challenging task of localizing subjects spatio-temporally in videos using only textual queries and no bounding box supervision. Inspired by recent advances in vision-language foundation models, we investigate their utility for WSTVG, leveraging their zero-shot grounding capabilities. However, we find that a simple adaptation lacks essential spatio-temporal grounding abilities. To bridge this gap, we introduce Tubelet Referral Grounding (TRG), which connects textual queries to tubelets to enable spatio-temporal predictions. Despite its promise, TRG struggles with compositional action understanding and dense scene scenarios. To address these limitations, we propose STPro, a progressive learning framework with two key modules: Sub-Action Temporal Curriculum Learning (SA-TCL), which incrementally builds compositional action understanding, and Congestion-Guided Spatial Curriculum Learning (CG-SCL), which adapts the model to complex scenes by spatially increasing task difficulty. STPro achieves state-of-the-art results on three benchmark datasets, with improvements of 1.0% on VidSTG-Declarative and 3.0% on HCSTVG-v1.

Pre-trained on tremendous image-text pairs, vision-language models like CLIP have demonstrated promising zero-shot generalization across numerous image-based tasks. However, extending these capabilities to video tasks remains challenging due to limited labeled video data and high training costs. Recent video prompting methods attempt to adapt CLIP for video tasks by introducing learnable prompts, but they typically rely on a single static prompt for all video sequences, overlooking the diverse temporal dynamics and spatial variations that exist across frames. This limitation significantly hinders the model's ability to capture essential temporal information for effective video understanding. To address this, we propose an integrated Spatial-TempOral dynamic Prompting (STOP) model which consists of two complementary modules, the intra-frame spatial prompting and inter-frame temporal prompting. Our intra-frame spatial prompts are designed to adaptively highlight discriminative regions within each frame by leveraging intra-frame attention and temporal variation, allowing the model to focus on areas with substantial temporal dynamics and capture fine-grained spatial details. Additionally, to highlight the varying importance of frames for video understanding, we further introduce inter-frame temporal prompts, dynamically inserting prompts between frames with high temporal variance as measured by frame similarity. This enables the model to prioritize key frames and enhances its capacity to understand temporal dependencies across sequences. Extensive experiments on various video benchmarks demonstrate that STOP consistently achieves superior performance against state-of-the-art methods. The code is available at https://github.com/zhoujiahuan1991/CVPR2025-STOP

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.

Recent text-to-image (T2I) diffusion models have demonstrated remarkable capabilities in visual synthesis, yet their performance heavily relies on the quality of input prompts. However, optimizing discrete prompts remains challenging because the discrete nature of tokens prevents the direct application of the gradient descent method and the vast search space of possible token combinations. As a result, existing approaches either suffer from quantization errors when employing continuous optimization techniques or become trapped in local optima due to coordinate-wise greedy search. In this paper, we propose STEPS, a novel Sequential probability Tensor Estimation approach for hard Prompt Search. Our method reformulates discrete prompt optimization as a sequential probability tensor estimation problem, leveraging the inherent low-rank characteristics to address the curse of dimensionality. To further improve the computational efficiency, we develop a memory-bounded sampling approach that shrinks the prompt space without the iteration step dependency while preserving sequential optimization dynamics. Extensive experiments on various public datasets demonstrate that our method consistently outperforms existing approaches in T2I generation, cross-model prompt transferability, and harmful prompt optimization, validating the effectiveness of the proposed framework.

Video Large Language Models (Video-LLMs) have recently shown strong performance in basic video understanding tasks, such as captioning and coarse-grained question answering, but struggle with compositional reasoning that requires multi-step spatio-temporal inference across object relations, interactions, and events. The hurdles to enhancing this capability include extensive manual labor, the lack of spatio-temporal compositionality in existing training data and the absence of explicit reasoning supervision. In this paper, we propose STEP, a novel graph-guided self-training method that enables Video-LLMs to generate reasoning-rich fine-tuning data from any raw videos to improve itself. Specifically, we first induce Spatio-Temporal Scene Graph (STSG) representation of diverse videos to capture fine-grained, multi-granular video semantics. Then, the STSGs guide the derivation of multi-step reasoning Question-Answer (QA) data with Chain-of-Thought (CoT) rationales. Both answers and rationales are integrated as training objective, aiming to enhance model's reasoning abilities by supervision over explicit reasoning steps. Experimental results demonstrate the effectiveness of STEP across models of varying scales, with a significant 21.3% improvement in tasks requiring three or more reasoning steps. Furthermore, it achieves superior performance with a minimal amount of self-generated rationale-enriched training samples in both compositional reasoning and comprehensive understanding benchmarks, highlighting the broad applicability and vast potential.

Diffusion probabilistic model is becoming the cornerstone of data generation, especially generating high-quality images. As an extension, video diffusion generation is in urgent need of a principled temporal-sequence diffusion way, while the spatial-domain diffusion dominates most video diffusion methods. In this work, we propose an explicit Spatio-Temporal Dual Diffusion (STDD) method by principledly extending the standard diffusion model to a spatio-temporal diffusion model for joint spatial and temporal noise propagation/reduction. Mathematically, an analysable dual diffusion process is derived to accumulate noises/information in temporal sequence as well as spatial domain. Correspondingly, we theoretically derive a spatio-temporal probabilistic reverse diffusion process and propose an accelerated sampling way to reduce the inference cost. In principle, the spatio-temporal dual diffusion enables the information of previous frames to be transferred to the current frame, which thus could be beneficial for video consistency. Extensive experiments demonstrate that our proposed STDD is more competitive over the state-of-the-art methods in the task of video generation/prediction as well as text-to-video generation.

3D occupancy and scene flow offer a detailed and dynamic representation of 3D scene. Recognizing the sparsity and complexity of 3D space, previous vision-centric methods have employed implicit learning-based approaches to model spatial and temporal information. However, these approaches struggle to capture local details and diminish the model's spatial discriminative ability. To address these challenges, we propose a novel explicit state-based modeling method designed to leverage the occupied state to renovate the 3D features. Specifically, we propose a sparse occlusion-aware attention mechanism, integrated with a cascade refinement strategy, which accurately renovates 3D features with the guidance of occupied state information. Additionally, we introduce a novel method for modeling long-term dynamic interactions, which reduces computational costs and preserves spatial information. Compared to the previous state-of-the-art methods, our efficient explicit renovation strategy not only delivers superior performance in terms of RayIoU and mAVE for occupancy and scene flow prediction but also markedly reduces GPU memory usage during training, bringing it down to 8.7GB. Our code is available on https://github.com/lzzzzzm/STCOcc

Extracting geometric edges from unstructured point clouds remains a significant challenge, particularly in thin-walled structures that are commonly found in everyday objects. Traditional geometric methods and recent learning-based approaches frequently struggle with these structures, as both rely heavily on sufficient contextual information from local point neighborhoods. However, 3D measurement data of thin-walled structures often lack the accurate, dense, and regular neighborhood sampling required for reliable edge extraction, resulting in degraded performance. In this work, we introduce STAR-Edge, a novel approach designed for detecting and refining edge points in thin-walled structures. Our method leverages a unique representation, the local spherical curve, to create structure-aware neighborhoods that emphasize co-planar points while reducing interference from close-by, non-co-planar surfaces. This representation is transformed into a rotation-invariant descriptor, which, combined with a lightweight multi-layer perceptron, enables robust edge point classification even in the presence of noise and sparse or irregular sampling. Besides, we also use the local spherical curve representation to estimate more precise normals and introduce an optimization function to project initially identified edge points exactly on the true edges. Experiments conducted on the ABC dataset and thin-walled structure-specific datasets demonstrate that STAR-Edge outperforms existing edge detection methods, showcasing better robustness under various challenging conditions. The source code is available at https://github.com/Miraclelzk/STAR-Edge.

Spiking Neural Networks (SNNs) have gained significant attention due to their biological plausibility and energy efficiency, making them promising alternatives to Artificial Neural Networks (ANNs). However, the performance gap between SNNs and ANNs remains a substantial challenge hindering the widespread adoption of SNNs. In this paper, we propose a Spatial-Temporal Attention Aggregator SNN (STAA-SNN) framework, which dynamically focuses on and captures both spatial and temporal dependencies. First, we introduce a spike-driven self-attention mechanism specifically designed for SNNs. Additionally, we pioneeringly incorporate position encoding to integrate latent temporal relationships into the incoming features. For spatial-temporal information aggregation, we employ step attention to selectively amplify relevant features to variant steps. Finally, we implement a time-step random dropout strategy to avoid local optima. The framework demonstrates exceptional performance across diverse datasets and exhibits strong generalization capabilities. Notably, STAA-SNN achieves state-of-the-art results on neuromorphic datasets CIFAR10-DVS of 82.10% and with performances of 97.14%, 82.05% and 70.40% on the static datasets CIFAR-10, CIFAR-100 and ImageNet, respectively. Furthermore, this model exhibits improved performance ranging from 0.33% to 2.80% with fewer time steps.

Most state-of-the-art trackers adopt one-stream paradigm, using a single Vision Transformer for joint feature extraction and relation modeling of template and search region images. However, relation modeling between different image patches exhibits significant variations. For instance, background regions dominated by target-irrelevant information require reduced attention allocation, while foreground, particularly boundary areas, need to be be emphasized. A single model may not effectively handle all kinds of relation modeling simultaneously. In this paper, we propose a novel tracker called SPMTrack based on mixture-of-experts tailored for visual tracking task (TMoE), combining the capability of multiple experts to handle diverse relation modeling more flexibly. Benefiting from TMoE, we extend relation modeling from image pairs to spatio-temporal context, further improving tracking accuracy with minimal increase in model parameters. Moreover, we employ TMoE as a parameter-efficient fine-tuning method, substantially reducing trainable parameters, which enables us to train SPMTrack of varying scales efficiently and preserve the generalization ability of pretrained models to achieve superior performance. We conduct experiments on seven datasets, and experimental results demonstrate that our method significantly outperforms current state-of-the-art trackers. The source code is available at https://github.com/WenRuiCai/SPMTrack.

3D Gaussian Splatting-based indoor open-world free-view synthesis approaches have shown significant performance with dense input images. However, they exhibit poor performance when confronted with sparse inputs, primarily due to the sparse distribution of Gaussian points and insufficient view supervision. To relieve these challenges, we propose SPC-GS, leveraging Scene-layout-based Gaussian Initialization (SGI) and Semantic-Prompt Consistency (SPC) Regularization for open-world free view synthesis with sparse inputs. Specifically, SGI provides a dense, scene-layout-based Gaussian distribution by utilizing view-changed images generated from the video generation model and view-constraint Gaussian points densification. Additionally, SPC mitigates limited view supervision by employing semantic-prompt-based consistency constraints developed by SAM2. This approach leverages available semantics from training views, serving as instructive prompts, to optimize visually overlapping regions in novel views with 2D and 3D consistency constraints. Extensive experiments demonstrate the superior performance of SPC-GS across Replica and ScanNet benchmarks. Notably, our SPC-GS achieves a 3.06 dB gain in PSNR for reconstruction quality and a 7.3% improvement in mIoU for open-world semantic segmentation.

Recent efforts in Gaussian-Splat-based Novel View Synthesis can achieve photorealistic rendering; however, such capability is limited in sparse-view scenarios due to sparse initialization and over-fitting floaters. Recent progress in depth estimation and alignment can provide dense point cloud using few views; however, the resulting pose accuracy is suboptimal. In this work, we present SPARS3R, which combines the advantages of accurate pose estimation from Structure-from-Motion and dense point cloud from depth estimation. To this end, SPARS3R first performs a Global Fusion Alignment process that maps a prior dense point cloud to a sparse point cloud from Structure-from-Motion based on triangulated correspondences. RANSAC is applied during this process to distinguish inliers and outliers. SPARS3R then performs a second, Semantic Outlier Alignment step, which extracts semantically coherent regions around the outliers and performs local alignment in these regions. Along with several improvements in the evaluation process, we demonstrate that SPARS3R can achieve photorealistic rendering with sparse images and significantly outperforms existing approaches.

Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications. Existing approaches require prompt tuning or architectural adaptations, limiting zero-shot applicability. Our work proposes a novel solution treating VLMs as black boxes, leveraging scores without training data or ground truth. We make two contributions. First, we find that VLM scores suffer from image- and prompt-specific biases, and that simple standardization is surprisingly effective at removing these and boosting MLR performance. And second, we introduce compound prompts grounded in realistic object combinations. Our analysis reveals "AND"/"OR" signal ambiguities that cause maximum compound scores to be surprisingly suboptimal compared to second-highest scores. We introduce an adaptive fusion method to address this issue. Our method enhances other zero-shot approaches, consistently improving their results. Experiments show superior mean Average Precision (mAP) compared to methods requiring training data, achieved through refined object ranking for robust zero-shot MLR. Code can be found at https://github.com/kjmillerCURIS/SPARC.

We study the problem of single-image 3D object reconstruction. Recent works have diverged into two directions: regression-based modeling and generative modeling. Regression methods efficiently infer visible surfaces, but struggle with occluded regions. Generative methods handle uncertain regions better by modeling distributions, but are computationally expensive and the generation is often misaligned with visible surfaces. In this paper, we present SPAR3D, a novel two-stage approach aiming to take the best of both directions. The first stage of SPAR3D generates sparse 3D point clouds using a lightweight point diffusion model, which has a fast sampling speed. The second stage uses both the sampled point cloud and the input image to create highly detailed meshes. Our two-stage design enables probabilistic modeling of the ill-posed single-image 3D task while maintaining high computational efficiency and great output fidelity. Using point clouds as an intermediate representation further allows for interactive user edits. Evaluated on diverse datasets, SPAR3D demonstrates superior performance over previous state-of-the-art methods, at an inference speed of 0.7 seconds. Project page with code and model: https://spar3d.github.io

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.

The integration of Vision-Language Models (VLMs) into autonomous driving systems has shown promise in addressing key challenges such as learning complexity, interpretability, and common-sense reasoning. However, existing approaches often struggle with efficient integration and real-time decision-making due to computational demands. In this paper, we introduce SOLVE, an innovative framework that synergizes VLMs with end-to-end (E2E) models to enhance autonomous vehicle planning. Our approach emphasizes knowledge sharing at the feature level through a shared visual encoder, enabling comprehensive interaction between VLM and E2E components. We propose a Trajectory Chain-of-Thought (T-CoT) paradigm, which progressively refines trajectory predictions, reducing uncertainty and improving accuracy. By employing a temporal decoupling strategy, SOLVE achieves efficient asynchronous cooperation, aligning high-quality VLM outputs with E2E real-time performance. Evaluated on the nuScenes dataset, our method demonstrates significant improvements in trajectory prediction accuracy, paving the way for more robust and reliable autonomous driving systems.

Human beings are social animals. How to equip 3D autonomous characters with similar social intelligence that can perceive, understand and interact with humans remains an open yet foundamental problem. In this paper, we introduce SOLAMI, the first end-to-end Social vision-Language-Action (VLA) Modeling framework for Immersive interaction with 3D autonomous characters. Specifically, SOLAMI builds 3D autonomous characters from three aspects: 1) Social VLA Architecture: We propose a unified social VLA framework to generate multimodal response (speech and motion) based on the user's multimodal input to drive the character for social interaction. 2) Interactive Multimodal Data: We present SynMSI, a synthetic multimodal social interaction dataset generated by an automatic pipeline using only existing motion datasets to address the issue of data scarcity. 3) Immersive VR Interface: We develop a VR interface that enables users to immersively interact with these characters driven by various architectures. Extensive quantitative experiments and user studies demonstrate that our framework leads to more precise and natural character responses (in both speech and motion) that align with user expectations with lower latency.

Anchor-based 3D Gaussian splatting (3D-GS) exploits anchor features in 3D Gaussian prediction, which has achieved impressive 3D rendering quality with reduced Gaussian redundancy. On the other hand, it often encounters the dilemma among anchor features, model size, and rendering quality - large anchor features lead to large 3D models and high-quality rendering whereas reducing anchor features degrades Gaussian attribute prediction which leads to clear artifacts in the rendered textures and geometries. We design SOGS, an anchor-based 3D-GS technique that introduces second-order anchors to achieve superior rendering quality and reduced anchor features and model size simultaneously. Specifically, SOGS incorporates covariance-based second-order statistics and correlation across feature dimensions to augment features within each anchor, compensating for the reduced feature size and improving rendering quality effectively. In addition, it introduces a selective gradient loss to enhance the optimization of scene textures and scene geometries, leading to high-quality rendering with small anchor features. Extensive experiments over multiple widely adopted benchmarks show that SOGS achieves superior rendering quality in novel view synthesis with clearly reduced model size.

Existing view transformations in vision-centric 3D Semantic Scene Completion (SSC) inevitably experience erroneous feature duplication in the reconstructed voxel space due to occlusions, leading to a dilution of informative contexts. Furthermore, semantic classes exhibit high variability in their appearance in real-world driving scenarios. To address these issues, we introduce a novel 3D SSC method, called SOAP, including two key components: an occluded region-aware view projection and a scene-adaptive decoder. The occluded region-aware view projection effectively converts 2D image features into voxel space, refining the duplicated features of occluded regions using information gathered from previous observations. The scene-adaptive decoder guides query embeddings to learn diverse driving environments based on a comprehensive semantic repository. Extensive experiments validate that the proposed SOAP significantly outperforms existing methods for the vision-centric 3D SSC on automated driving datasets, SemanticKITTI and SSCBench. Code is available at https://github.com/gywns6287/SOAP.