CVPR 2025 论文列表

Diffusion models have achieved significant progress in both image and video generation while still suffering from huge computation costs. As an effective solution, rectified flow aims to rectify the diffusion process of diffusion models into a straight line for few-step and even one-step generation. However, in this paper, we suggest that the original training pipeline of reflow is not optimal and introduce two techniques to improve it. Firstly, we introduce progressive reflow, which progressively reflows the diffusion models in local timesteps until the whole diffusion progresses, reducing the difficulty of flow matching. Second, we introduce aligned v-prediction, which highlights the importance of direction matching in flow matching over magnitude matching. Experimental results on SDv1.5 and SDXL demonstrate the effectiveness of our method, for example, conducting on SDv1.5 achieves an FID of 10.70 on MSCOCO2014 validation set with only 4 sampling steps, close to our teacher model (32 DDIM steps, FID = 10.05). Our codes will be released at Github.

Recent advancements in trajectory-guided video generation have achieved notable progress. However, existing models still face challenges in generating object motions with potentially changing 6D poses under wide-range rotations, due to limited 3D understanding. To address this problem, we introduce PoseTraj, a pose-aware video dragging model for generating 3D-aligned motion from 2D trajectories. Our method adopts a novel two-stage pose-aware pretraining framework, improving 3D understanding across diverse trajectories. Specifically, we propose a large-scale synthetic dataset PoseTraj-10k, containing 10k videos of objects following rotational trajectories, and enhance the model perception of object pose changes by incorporating 3D bounding boxes as intermediate supervision signals. Following this, we fine-tune the trajectory-controlling module on real-world videos, applying an additional camera-disentanglement module to further refine motion accuracy. Experiments on various benchmark datasets demonstrate that our method not only excels in 3D pose-aligned dragging for rotational trajectories but also outperforms existing baselines in trajectory accuracy and video quality.

Reflection removal is challenging due to complex light interactions, where reflections obscure important details and hinder scene understanding. Polarization naturally provides a powerful cue to distinguish between reflected and transmitted light, enabling more accurate reflection removal. However, existing methods often rely on small-scale or synthetic datasets, which fail to capture the diversity and complexity of real-world scenarios. To this end, we construct a large-scale dataset, PolaRGB, for Polarization-based reflection removal of RGB images, which enables us to train models that generalize effectively across a wide range of real-world scenarios. The PolaRGB dataset contains 6,500 well-aligned mixed-transmission image pairs, 8xlarger than existing polarization datasets, and is the first to include both RGB and polarization images captured across diverse indoor and outdoor environments with varying lighting conditions. Besides, to fully exploit the potential of polarization cues for reflection removal, we introduce PolarFree, which leverages diffusion process to generate reflection-free cues for accurate reflection removal. Extensive experiments show that PolarFree significantly enhances image clarity in challenging reflective scenarios, setting a new benchmark for polarized imaging and reflection removal. Code and dataset are available at https://github.com/mdyao/PolarFree.

As a widely adopted technique in data transmission, video compression effectively reduces the size of files, making it possible for real-time cloud computing. However, it comes at the cost of visual quality, posing challenges to the robustness of downstream vision models. In this work, we present a versatile codec-aware enhancement framework that reuses codec information to adaptively enhance videos under different compression settings, assisting various downstream vision tasks without introducing computation bottleneck. Specifically, the proposed codec-aware framework consists of a compression-aware adaptation (CAA) network that employs a hierarchical adaptation mechanism to estimate parameters of the frame-wise enhancement network, namely the bitstream-aware enhancement (BAE) network. The BAE network further leverages temporal and spatial priors embedded in the bitstream to effectively improve the quality of compressed input frames. Extensive experimental results demonstrate the superior quality enhancement performance of our framework over existing enhancement methods, as well as its versatility in assisting multiple downstream tasks on compressed videos as a plug-and-play module. Code and models are available at https://huimin-zeng.github.io/PnP-VCVE/.

Standard video codecs are rate-distortion optimization machines, where distortion is typically quantified using PSNR versus the source. However, it is now widely accepted that increasing PSNR does not necessarily translate to better visual quality. In this paper, a better balance between perception and fidelity is targeted, in order to provide for significant rate savings over state-of-the-art standards-based video codecs. Specifically, pre- and postprocessing neural networks are proposed that enhance the coding efficiency of standard video codecs when benchmarked with an array of well-established perceptual quality scores. These "neural wrapper" elements are end-to-end trained with a neural codec module serving as a differentiable proxy for standard video codecs. The codec proxy is jointly optimized with the pre- and post components, via a novel two-phase pretraining strategy and end-to-end iterative refinement with stop-gradient. This allows the neural pre- and postprocessor to learn to embed, remove and recover information in a codec-aware manner, thus improving its rate-quality performance. A single neural-wrapper model is thereby established and used for the entire rate-quality curve without needing any downscaling or upscaling. The trained model is tested with the AV1 and VVC standard codecs via an array of well-established objective quality scores (SSIM, MS-SSIM, VMAF, AVQT), as well as mean opinion scores (MOS) derived from ITU-T P.910 subjective testing. Experimental results show that the proposed approach improves all quality scores, with -18.5% average Bjontegaard Delta-rate (BD-rate) saving over all objective scores and MOS improvement over both standard codecs. This illustrates the significant potential of neural wrapper components over standards-based video coding.

Pre-trained video generation models hold great potential for generative video super-resolution (VSR). However, adapting them for full-size VSR, as most existing methods do, suffers from unnecessary intensive full-attention computation and fixed output resolution. To overcome these limitations, we make the first exploration into utilizing video diffusion priors for patch-wise VSR.This is non-trivial because pre-trained video diffusion models are not native for patch-level detail generation. To mitigate this challenge, we propose an innovative approach, called PatchVSR, which integrates a dual-stream adapter for conditional guidance. The patch branch extracts features from input patches to maintain content fidelity while the global branch extracts context features from the resized full video to bridge the generation gap caused byincomplete semantics of patches.Particularly, we also inject the patch's location information into the model to better contextualize patch synthesis within the global video frame.Experiments demonstrate that our method can synthesize high-fidelity, high-resolution details at the patch level. A tailor-made multi-patch joint modulation is proposed to ensure visual consistency across individually enhanced patches. Due to the flexibility of our patch-based paradigm, we can achieve highly competitive 4K VSR based on a 512x512 resolution base model, with extremely high efficiency.

Large Vision-Language Models (VLMs) have been extended to understand both images and videos. Visual token compression is leveraged to reduce the considerable token length of visual inputs. To meet the needs of different tasks, existing high-performance models usually process images and videos separately with different token compression strategies, limiting the capabilities of combining images and videos. To this end, we extend each image into a "static" video and introduce a unified token compression strategy called Progressive Visual Token Compression (PVC), where the tokens of each frame are progressively encoded and adaptively compressed to supplement the information not extracted from previous frames. Video tokens are efficiently compressed with exploiting the inherent temporal redundancy. Images are repeated as static videos, and the spatial details can be gradually supplemented in multiple frames. PVC unifies the token compressing of images and videos. With a limited number of tokens per frame (64 tokens by default), spatial details and temporal changes can still be preserved. Experiments show that our model achieves state-of-the-art performance across various video understanding benchmarks, including long video tasks and fine-grained short video tasks. Meanwhile, our unified token compression strategy incurs no performance loss on image benchmarks, particularly in detail-sensitive tasks.

Applying pre-trained models to assist point cloud understanding has recently become a mainstream paradigm in 3D perception. However, existing application strategies are straightforward, utilizing only the final output of the pre-trained model for various task heads. It neglects the rich complementary information in the intermediate layer, thereby failing to fully unlock the potential of pre-trained models. To overcome this limitation, we propose an orthogonal solution: Point Mamba Adapter (PMA), which constructs an ordered feature sequence from all layers of the pre-trained model and leverages Mamba to fuse all complementary semantics, thereby promoting comprehensive point cloud understanding. Constructing this ordered sequence is non-trivial due to the inherent isotropy of 3D space. Therefore, we further propose a geometry-constrained gate prompt generator (G2PG) shared across different layers, which applies shared geometric constraints to the output gates of the Mamba and dynamically optimizes the spatial order, thus enabling more effective integration of multi-layer information. Extensive experiments conducted on challenging point cloud datasets across various tasks demonstrate that our PMA elevates the capability for point cloud understanding to a new level by fusing diverse complementary intermediate features. Code is available at https://github.com/zyh16143998882/PMA.

Geologic map, as a fundamental diagram in geology science, provides critical insights into the structure and composition of Earth's subsurface and surface. These maps are indispensable in various fields, including disaster assessment, resource exploration, and civil engineering. Despite their significance, current Multimodal Large Language Models (MLLMs) often fall short in geologic map understanding. This gap is primarily due to the challenging nature of cartographic generalization, which involves handling high-resolution map, managing multiple associated components, and requiring domain-specific knowledge. To quantify this gap, we construct **GeoMap-Bench**, the first-ever benchmark for evaluating MLLMs in geologic map understanding, which assesses the full-scale abilities in extracting, referring, grounding, reasoning, and analyzing. To bridge this gap, we introduce **GeoMap-Agent**, the inaugural agent designed for geologic map understanding, which features three modules: Hierarchical Information Extraction (HIE), Domain Knowledge Injection (DKI), and Prompt-enhanced Question Answering (PEQA). Inspired by the interdisciplinary collaboration among human scientists, an AI expert group acts as consultants, utilizing a diverse tool pool to comprehensively analyze questions. Through comprehensive experiments, GeoMap-Agent achieves an overall score of 0.811 on GeoMap-Bench, significantly outperforming 0.369 of GPT-4o. Our work, em**P**owering g**E**ologic m**A**p holisti**C** und**E**rstanding (**PEACE**) with MLLMs, paves the way for advanced AI applications in geology, enhancing the efficiency and accuracy of geological investigations. The code and data are available at https://github.com/microsoft/PEACE.

We present PAVE, a framework for adapting pre-trained video large language models (Video-LLMs) to downstream tasks that incorporate side-channel signals, such as audio, camera pose, or high frame rate videos. PAVE introduces a lightweight adaptation strategy called "patching", which adds a small number of parameters and operations to the base model without modifying its architecture or pre-trained weights. We demonstrate that PAVE effectively enhances pre-trained Video-LLMs with the cost of adding <1% additional FLOPs and parameters for diverse tasks, including audio-visual understanding, 3D reasoning, and multi-view video understanding, surpassing state-of-the-art task-specific models. Moreover, when applied to high frame rate videos, PAVE further improves video understanding, enhancing the performance of strong base models. Finally, our experiments show that our framework generalizes well across different Video-LLMs.

Multimodal Large Language Models (MLLMs) have significantly progressed in offline video understanding. However, applying these models to real-world scenarios, such as autonomous driving and human-computer interaction, presents unique challenges due to the need for real-time processing of continuous online video streams. To this end, this paper presents systematic efforts from three perspectives: evaluation benchmark, model architecture, and training strategy. First, we introduce OVBench, a comprehensive question-answering benchmark designed to evaluate models' ability to perceive, memorize, and reason within online video contexts. It features 6 core task types across three temporal contexts--past, current, and future--forming 16 subtasks from diverse datasets. Second, we propose a new Pyramid Memory Bank (PMB) that effectively retains key spatiotemporal information in video streams. Third, we proposed an offline-to-online learning paradigm, designing an interleaved dialogue format for online video data and constructing an instruction-tuning dataset tailored for online video training. This framework led to the development of VideoChat-Online, a robust and efficient model for online video understanding. Despite the lower computational cost and higher efficiency, VideoChat-Online outperforms existing state-of-the-art offline and online models across popular offline video benchmarks and OVBench, demonstrating the effectiveness of our model architecture and training strategy.

Video large language models (Video-LLMs) can temporally ground language queries and retrieve video moments. Yet, such temporal comprehension capabilities are neither well-studied nor understood. So we conduct a study on prediction consistency -- a key indicator for robustness and trustworthiness of temporal grounding. After the model identifies an initial moment within the video content, we apply a series of probes to check if the model's responses align with this initial grounding as an indicator of reliable comprehension. Our results reveal that current Video-LLMs are sensitive to variations in video contents, language queries, and task settings, unveiling severe deficiencies in maintaining consistency. We further explore common prompting and instruction-tuning methods as potential solutions, but find that their improvements are often unstable. To that end, we propose event temporal verification tuning that explicitly accounts for consistency, and demonstrate significant improvements for both grounding and consistency. Our data and code are open-sourced at https://github.com/minjoong507/Consistency-of-Video-LLM.

Understanding fine-grained temporal dynamics is crucial in egocentric videos, where continuous streams capture frequent, close-up interactions with objects. In this work, we bring to light that current egocentric video question-answering datasets often include questions that can be answered using only few frames or commonsense reasoning, without being necessarily grounded in the actual video. Our analysis shows that state-of-the-art Multi-Modal Large Language Models (MLLMs) on these benchmarks achieve remarkably high performance using just text or a single frame as input. To address these limitations, we introduce EgoTempo, a dataset specifically designed to evaluate temporal understanding in the egocentric domain. EgoTempo emphasizes tasks that require integrating information across the entire video, ensuring that models would need to rely on temporal patterns rather than static cues or pre-existing knowledge. Extensive experiments on EgoTempo show that current MLLMs still fall short in temporal reasoning on egocentric videos, and thus we hope EgoTempo will catalyze new research in the field and inspire models that better capture the complexity of temporal dynamics. Dataset and code are available at https://github.com/google-research-datasets/egotempo.git.

The rapid advancement of multi-modal language models (MLLMs) like GPT-4o has propelled the development of Omni language models, designed to process and proactively respond to continuous streams of multi-modal data. Despite their potential, evaluating their real-world interactive capabilities in streaming video contexts remains a formidable challenge. In this work, we introduce OmniMMI, a comprehensive multi-modal interaction benchmark tailored for OmniLLMs in streaming video contexts. OmniMMI encompasses over 1,121 videos and 2,290 questions, addressing two critical yet underexplored challenges in existing video benchmarks: streaming video understanding and proactive reasoning, across six distinct subtasks. Moreover, we propose a novel framework, Multi-modal Multiplexing Modeling (M4), designed to enable an inference-efficient streaming model that can see, listen while generating.

We present Omni-RGPT, a multimodal large language model designed to facilitate region-level comprehension for both images and videos. To achieve consistent region representation across spatio-temporal dimensions, we introduce Token Mark, a set of tokens highlighting the target regions within the visual feature space. These tokens are directly embedded into spatial regions using region prompts (e.g., boxes or masks) and simultaneously incorporated into the text prompt to specify the target, establishing a direct connection between visual and text tokens. To further support robust video understanding without requiring tracklets, we introduce an auxiliary task that guides Token Mark by leveraging the consistency of the tokens, enabling stable region interpretation across the video. Additionally, we introduce a large-scale region-level video instruction dataset (RegVID-300k). Omni-RGPT achieves state-of-the-art results on image and video-based commonsense reasoning benchmarks while showing strong performance in captioning and referring expression comprehension tasks.

Simple as it seems, moving an object to another location within an image is, in fact, a challenging image-editing task that requires re-harmonizing the lighting, adjusting the pose based on perspective, accurately filling occluded regions, and ensuring coherent synchronization of shadows and reflections while maintaining the object identity. In this paper, we present ObjectMover, a generative model that can perform object movement in highly challenging scenes. Our key insight is that we model this task as a sequence-to-sequence problem and fine-tune a video generation model to leverage its knowledge of consistent object generation across video frames. We show that with this approach, our model is able to adjust to complex real-world scenarios, handling extreme lighting harmonization and object effect movement. As large-scale data for object movement are unavailable, we construct a data generation pipeline using a modern game engine to synthesize high-quality data pairs. We further propose a multi-task learning strategy that enables training on real-world video data to improve the model generalization. Through extensive experiments, we demonstrate that ObjectMover achieves outstanding results and adapts well to real-world scenarios.

Egocentric video grounding is a crucial task for embodied intelligence applications, distinct from exocentric video moment localization. Existing methods primarily focus on the distributional differences between egocentric and exocentric videos but often neglect key characteristics of egocentric videos and the fine-grained information emphasized by question-type queries. To address these limitations, we propose OSGNet, an Object-Shot enhanced Grounding Network for egocentric video. Specifically, we extract object information from videos to enrich video representation, particularly for objects highlighted in the textual query but not directly captured in the video features. Additionally, we analyze the frequent shot movements inherent to egocentric videos, leveraging these features to extract the wearer's attention information, which enhances the model's ability to perform modality alignment. Experiments conducted on three datasets demonstrate that OSGNet achieves state-of-the-art performance, validating the effectiveness of our approach. Our code can be found at https://github.com/Yisen-Feng/OSGNet.

Temporal Awareness, the ability to reason dynamically based on the timestamp when a question is raised, is the key distinction between offline and online video LLMs. Unlike offline models, which rely on complete videos for static, post hoc analysis, online models process video streams incrementally and dynamically adapt their responses based on the timestamp at which the question is posed. Despite its significance, temporal awareness has not been adequately evaluated in existing benchmarks. To fill this gap, we present OVO-Bench (Online-VideO-Benchmark), a novel video benchmark that emphasizes the importance of timestamps for advanced online video understanding capability benchmarking. OVO-Bench evaluates the ability of video LLMs to reason and respond to events occurring at specific timestamps under three distinct scenarios: (1) Backward tracing: trace back to past events to answer the question. (2) Real-time understanding: understand and respond to events as they unfold at the current timestamp. (3) Forward active responding: delay the response until sufficient future information becomes available to answer the question accurately. OVO-Bench comprises 12 tasks, featuring 644 unique videos and approximately human-curated 2,800 fine-grained meta-annotations with precise timestamps. We combine automated generation pipelines with human curation. With these high-quality samples, we further developed an evaluation pipeline to systematically query video LLMs along the video timeline. Evaluations of nine Video-LLMs reveal that, despite advancements on traditional benchmarks, current models struggle with online video understanding, showing a significant gap compared to human agents. We hope OVO-Bench will drive progress in video LLMs and inspire future research in online video reasoning. Our benchmark and code can be accessed at https://joeleelyf.github.io/OVO-Bench.

Video Large Language Models (Vid-LLMs) have made remarkable advancements in comprehending video content for QA dialogue. However, they struggle to extend this visual understanding to tasks requiring precise temporal localization, known as Video Temporal Grounding (VTG). To address this, we introduce Number-Prompt (NumPro), a novel method that empowers Vid-LLMs to bridge visual comprehension with temporal grounding by adding unique numerical identifiers to each video frame. Treating a video as a sequence of numbered frame images, NumPro transforms VTG into an intuitive process: flipping through manga panels in sequence. This allows Vid-LLMs to "read" event timelines, accurately linking visual content with corresponding temporal information. Our experiments demonstrate that NumPro significantly boosts VTG performance of top-tier Vid-LLMs without additional computational cost. Furthermore, fine-tuning on a NumPro-enhanced dataset defines a new state-of-the-art for VTG, surpassing previous top-performing methods by up to 6.9% in mIoU for moment retrieval and 8.5% in mAP for highlight detection. The code is available at https://github.com/yongliang-wu/NumPro.