CVPR 2025 论文列表

Depth estimation is a core problem in robotic perception and vision tasks, but 3D reconstruction from a single image presents inherent uncertainties. Current depth estimation models primarily rely on inter-image relationships for supervised training, often overlooking the intrinsic information provided by the camera itself. We propose a method that embodies the camera model and its physical characteristics into a deep learning model, computing embodied scene depth through real-time interactions with road environments. The model can calculate embodied scene depth in real-time based on immediate environmental changes using only the intrinsic properties of the camera, without any additional equipment. By combining embodied scene depth with RGB image features, the model gains a comprehensive perspective on both geometric and visual details. Additionally, we incorporate text descriptions containing environmental content and depth information as priors for scene understanding, enriching the model's perception of objects. This integration of image and language -- two inherently ambiguous modalities -- leverages their complementary strengths for monocular depth estimation. The real-time nature of the embodied language and depth prior model ensures that the model can continuously adjust its perception and behavior in dynamic environments. Experimental results show that the embodied depth estimation method enhances model performance across different scenes.

Recent advances in human motion prediction (HMP) have shifted focus from isolated motion data to integrating human-scene correlations. In particular, the latest methods leverage human gaze points, using their spatial coordinates to indicate intent--where a person might move within a 3D environment. Despite promising trajectory results, these methods often produce inaccurate poses by overlooking the semantic implications of gaze, specifically the affordances of observed objects, which indicate the possible interactions. To address this, we propose GAP3DS, an affordance-aware HMP model that utilizes gaze-informed object affordances to improve HMP in complex 3D environments. GAP3DS incorporates a gaze-guided affordance learner to identify relevant objects in the scene and infer their affordances based on human gaze, thus contextualizing future human-object interactions. This affordance information, enriched with visual features and gaze data, conditions the generation of multiple human-object interaction poses, which are subsequently decoded into final motion predictions. Extensive experiments on two real-world datasets demonstrate that GAP3DS outperforms state-of-the-art methods in both trajectory and pose accuracy, producing more physically consistent and contextually grounded predictions. For more details and code, please refer to the project page.

Visual narrative generation transforms textual narratives into sequences of images illustrating the content of the text. However, generating visual narratives that are faithful to the input text and self-consistent across generated images remains an open challenge, due to the lack of knowledge constraints used for planning the stories. In this work, we propose a new benchmark, VinaBench, to address this challenge. Our benchmark annotates the underlying commonsense and discourse constraints in visual narrative samples, offering systematic scaffolds for learning the implicit strategies of visual storytelling. Based on the incorporated narrative constraints, we further propose novel metrics to closely evaluate the consistency of generated narrative images and the alignment of generations with the input textual narrative. Our results across three generative vision models demonstrate that learning with VinaBench's knowledge constraints effectively improves the faithfulness and cohesion of generated visual narratives.

Recent advances in audio generation have focused on text-to-audio (T2A) and video-to-audio (V2A) tasks. However, T2A or V2A methods cannot generate holistic sounds (onscreen and off-screen). This is because T2A cannot generate sounds aligning with onscreen objects, while V2A cannot generate semantically complete (offscreen sounds missing). In this work, we address the task of holistic audio generation: given a video and a text prompt, we aim to generate both onscreen and offscreen sounds that are temporally synchronized with the video and semantically aligned with text and video. Previous approaches for joint text and video-to-audio generation often suffer from modality bias, favoring one modality over the other. To overcome this limitation, we introduce VinTAGe, a flow-based transformer model that jointly considers text and video to guide audio generation. Our framework comprises two key components: a Visual-Text Encoder and a Joint VT-SiT model. To reduce modality bias and improve generation quality, we employ pretrained uni-modal text-to-audio and video-to-audio generation models for additional guidance. Due to the lack of appropriate benchmarks, we also introduce VinTAGe-Bench, a dataset of 636 video-text-audio pairs containing both onscreen and offscreen sounds. Our comprehensive experiments on VinTAGe-Bench demonstrate that joint text and visual interaction is necessary for holistic audio generation. Furthermore, VinTAGe achieves state-of-the-art results on the VGGSound benchmark.We will release our pretrained models and the VinTAGe-Bench dataset to facilitate future research in this exciting field.

Neural implicit surface representation methods have recently shown impressive 3D reconstruction results. However, existing solutions struggle to reconstruct driving scenes due to their large size, highly complex nature and limited visual observation overlap.Hence, to achieve accurate reconstructions, additional supervision data such as LiDAR, strong geometric priors, and long training times are required.To tackle such limitations, we present ViiNeuS, a new hybrid implicit surface learning method that efficiently initializes the signed distance field to reconstruct large driving scenes from 2D street view images.ViiNeuS's hybrid architecture models two separate implicit fields: one representing the volumetric density of the scene, and another one representing the signed distance to the surface.To accurately reconstruct urban outdoor driving scenarios, we introduce a novel volume-rendering strategy that relies on self-supervised probabilistic density estimation to sample points near the surface and transition progressively from volumetric to surface representation. Our solution permits a proper and fast initialization of the signed distance field without relying on any geometric prior on the scene, compared to concurrent methods.By conducting extensive experiments on four outdoor driving datasets, we show that ViiNeuS can learn an accurate and detailed 3D surface scene representation in various driving scenarios while being two times faster to train compared to previous state-of-the-art solutions.

Egocentric and exocentric perspectives of human action differ significantly, yet overcoming this extreme viewpoint gap is critical for applications in augmented reality and robotics. We propose ViewpointRosetta, an approach that unlocks large-scale unpaired ego and exo video data to learn clip-level viewpoint-invariant video representations. Our framework introduces (1) a diffusion-based Rosetta Stone Translator (RST), which, leveraging a moderate amount of synchronized multi-view videos, serves as a translator in feature space to decipher the alignments between unpaired ego and exo data, and (2) a dual encoder that aligns unpaired data representations through contrastive learning with RST-based synthetic feature augmentation and soft alignment. To evaluate the learned features in a standardized setting, we construct a new cross-view benchmark using Ego-Exo4D, covering cross-view retrieval, action recognition, and skill assessment. Our framework demonstrates superior cross-view understanding compared to previous view-invariant learning and egocentric video representation learning approaches, and opens the door to bringing vast amounts of traditional third-person video to bear on the more nascent first-person setting.

This work explores whether a deep generative model can learn complex knowledge solely from visual input, in contrast to the prevalent focus on text-based models like large language models (LLMs). We develop VideoWorld, an auto-regressive video generation model trained on unlabeled video data, and test its knowledge acquisition abilities in video-based Go and robotic control tasks. Our experiments reveal two key findings: (1) video-only training provides sufficient information for learning knowledge, including rules, reasoning and planning capabilities, and (2) the representation of visual change is crucial for knowledge acquisition. To improve both the efficiency and efficacy of this process, we introduce the Latent Dynamics Model (LDM) as a key component of VideoWorld. Remarkably, VideoWorld reaches a 5-dan professional level in the Video-GoBench with just a 300-million-parameter model, without relying on search algorithms or reward mechanisms typical in reinforcement learning. In robotic tasks, VideoWorld effectively learns diverse control operations and generalizes across environments, approaching the performance of oracle models in CALVIN and RLBench. This study opens new avenues for knowledge acquisition from visual data, with all code, data, and models open-sourced for further research.

Long-form video understanding has been a challenging task due to the high redundancy in video data and the abundance of query-irrelevant information. To tackle this challenge, we propose VideoTree, a training-free framework which builds a query-adaptive and hierarchical video representation for LLM reasoning over long-form videos. First, VideoTree extracts query-relevant information from the input video through an iterative process, progressively refining the selection of keyframes based on their relevance to the query. Furthermore, VideoTree leverages the inherent hierarchical structure of long video data, which is often overlooked by existing LLM-based methods. Specifically, we incorporate multi-granularity information into a tree-based representation, allowing VideoTree to extract query-relevant details from long videos in a coarse-to-fine manner. This enables the model to effectively handle a wide range of video queries with varying levels of detail. Finally, VideoTree aggregates the hierarchical query-relevant information within the tree structure and feeds it into an LLM reasoning model to answer the query. Our experiments show that VideoTree improves both reasoning accuracy and efficiency compared to existing methods. Specifically, VideoTree outperforms the existing training-free approaches on the popular EgoSchema and NExT-QA benchmarks with less inference time, achieving 61.1% and 75.6% accuracy on the test set without additional video-specific training. Moreover, on the long split of Video-MME benchmark (average 44 minutes), the training-free VideoTree framework achieves better performance than the strong proprietary GPT-4V model and many other MLLMs that were extensively trained on video data. Our code is provided in the supplementary materials and will be made public.

We present an implicit video representation for occlusions, appearance, and motion disentanglement from monocular videos, which we refer to as Video Spatiotemporal Splines (VideoSPatS).Unlike previous methods that map time and coordinates to deformation and canonical colors, our VideoSPatS maps input coordinates into Spatial and Color Spline deformation fields Ds and Dc, which disentangle motion and appearance in videos. With spline-based parametrization, our method naturally generates temporally consistent flow and guarantees long-term temporal consistency, which is crucial for convincing video editing.Aided by additional prediction blocks, our VideoSPatS also performs layer separation between the latent video and the selected occluder. By disentangling occlusions, appearance, and motion, our method allows for better spatiotemporal modeling and editing of diverse videos, including in-the-wild talking head videos with challenging occlusions, shadows, and specularities while maintaining a reasonable canonical space for editing.We also present general video modeling results on the DAVIS, and CoDeF datasets, as well as our own talking head video dataset collected from open-source web videos. Extensive ablations show the combination of Ds and Dc under neural splines can overcome motion and appearance ambiguities, paving the way to more advanced video editing models.

Video Large Language Models (Video LLMs) have recently exhibited remarkable capabilities in general video understanding.However, they mainly focus on holistic comprehension and struggle with capturing fine-grained spatial and temporal details. Besides, the lack of high-quality object-level video instruction data and a comprehensive benchmark further hinders their advancements. To tackle these challenges, we introduce the VideoRefer Suite to empower Video LLM for finer-level spatial-temporal video understanding, i.e., enabling perception and reasoning on any objects throughout the video. Specially, we thoroughly develop VideoRefer Suite across three essential aspects: dataset, model, and benchmark. Firstly, we introduce a multi-agent data engine to meticulously curate a large-scale, high-quality object-level video instruction dataset, termed VideoRefer-700K. Next, we present the VideoRefer model, which equips a versatile spatial-temporal object encoder to capture precise regional and sequential representations. Finally, we meticulously create a VideoRefer-Bench to comprehensively assess the spatial-temporal understanding capability of a Video LLM, evaluating it across various aspects. Extensive experiments and analyses demonstrate that our VideoRefer model not only achieves promising performance on video referring benchmarks but also facilitates general video understanding capabilities. Our codes, models, and dataset will be made publicly available.

Customized text-to-video generation aims to produce high-quality videos that incorporate user-specified subject identities or motion patterns. However, existing methods mainly focus on personalizing a single concept, either subject identity or motion pattern, limiting their effectiveness for multiple subjects with the desired motion patterns. To tackle this challenge, we propose a unified framework VideoMage for video customization over both multiple subjects and their interactive motions. VideoMage employs subject and motion LoRAs to capture personalized content from user-provided images and videos, along with an appearance-agnostic motion learning approach to disentangle motion patterns from visual appearance. Furthermore, we develop a spatial-temporal composition scheme to guide interactions among subjects within the desired motion patterns. Extensive experiments demonstrate that VideoMage outperforms existing methods, generating coherent, user-controlled videos with consistent subject identities and interactions.

Recent advancements in video large multimodal models (LMMs) have significantly improved their video understanding and reasoning capabilities. However, their performance drops on out-of-distribution (OOD) tasks that are underrepresented in training data. Traditional methods like fine-tuning on OOD datasets are impractical due to high computational costs. While In-context learning (ICL) with demonstration examples has shown promising generalization performance in language tasks and image-language tasks without fine-tuning, applying ICL to video-language tasks faces challenges due to the limited context length in Video LMMs, as videos require longer token lengths. To address these issues, we propose VideoICL, a novel video in-context learning framework for OOD tasks that introduces a similarity-based relevant example selection strategy and a confidence-based iterative inference approach. This allows to select the most relevant examples and rank them based on similarity, to be used for inference. If the generated response has low confidence, our framework selects new examples and performs inference again, iteratively refining the results until a high-confidence response is obtained. This approach improves OOD video understanding performance by extending effective context length without incurring high costs. The experimental results on multiple benchmarks demonstrate significant performance gains, especially in domain-specific scenarios, laying the groundwork for broader video comprehension applications.

Generative methods for image and video editing use generative models as priors to perform edits despite incomplete information, such as changing the composition of 3D objects shown in a single image. Recent methods have shown promising composition editing results in the image setting, but in the video setting, editing methods have focused on editing object appearance, object motion, or camera motion, and as a result, methods to edit object composition in videos are still missing. We propose VideoHandles as a method for editing 3D object compositions in videos of static scenes with camera motion. Our approach allows editing the 3D position of a 3D object across all frames of a video in a temporally consistent manner. This is achieved by lifting intermediate features of a generative model to a 3D reconstruction that is shared between all frames, editing the reconstruction, and projecting the features on the edited reconstruction back to each frame. To the best of our knowledge, this is the first generative approach to edit object compositions in videos. Our approach is simple and training-free, while outperforming state-of-the-art image editing baselines.

Text-to-image (T2I) diffusion models have revolutionized visual content creation, but extending these capabilities to text-to-video (T2V) generation remains a challenge, particularly in preserving temporal consistency. Existing methods that aim to improve consistency often cause trade-offs such as reduced imaging quality and impractical computational time. To address these issues we introduce VideoGuide, a novel framework that enhances the temporal consistency of pretrained T2V models without the need for additional training or fine-tuning. Instead, VideoGuide leverages any pretrained video diffusion model (VDM) or itself as a guide during the early stages of inference, improving temporal quality by interpolating the guiding model's denoised samples into the sampling model's denoising process. The proposed method brings about significant improvement in temporal consistency and image fidelity, providing a cost-effective and practical solution that synergizes the strengths of various video diffusion models. Furthermore, we demonstrate prior distillation, revealing that base models can achieve enhanced text coherence by utilizing the superior data prior of the guiding model through the proposed method. Project Page: https://dohunlee1.github.io/videoguide.github.io/

Video super-resolution (VSR) models achieve temporal consistency but often produce blurrier results than their image-based counterparts due to limited generative capacity. This prompts the question: can we adapt a generative image upsampler for VSR while preserving temporal consistency? We introduce VideoGigaGAN, a new generative VSR model that combines high-frequency detail with temporal stability, building on the large-scale GigaGAN image upsampler. Simple adaptations of GigaGAN for VSR led to flickering issues, so we propose techniques to enhance temporal consistency. We validate the effectiveness of VideoGigaGAN by comparing it with state-of-the-art VSR models on public datasets and showcasing video results with 8x upsampling.

Fine-grained alignment between videos and text is challenging due to complex spatial and temporal dynamics in videos. Existing video-based Large Multimodal Models (LMMs) handle basic conversations but struggle with precise pixel-level grounding in videos. To address this, we introduce VideoGLaMM, a LMM designed for fine-grained pixel-level grounding in videos based on user-provided textual inputs. Our design seamlessly connects three key components: a Large Language Model, a dual vision encoder that emphasizes both spatial and temporal details, and a spatio-temporal decoder for accurate mask generation. This connection is facilitated via tunable V-L and L-V adapters that enable close Vision-Language (VL) alignment. The architecture is trained to synchronize both spatial and temporal elements of video content with textual instructions. To enable fine-grained grounding, we curate a multimodal dataset featuring detailed visually-grounded conversations using a semiautomatic annotation pipeline, resulting in a diverse set of 38k video-QA triplets along with 83k objects and 671k masks. We evaluate VideoGLaMM on three challenging tasks: Grounded Conversation Generation, Visual Grounding, and Referring Video Segmentation. Experimental results show that our model consistently outperforms existing approaches across all three tasks.

Vision-language foundation models have shown impressive capabilities across various zero-shot tasks, including training-free localization and grounding, primarily focusing on localizing objects in images. However, leveraging those capabilities to localize actions and events in videos is challenging, as actions have less physical outline and are usually described by higher-level concepts.In this work, we propose VideoGEM, the first training-free spatial action grounding method based on pretrained image- and video-language backbones. Namely, we adapt the self-self attention formulation of GEM to spatial activity grounding. We observe that high-level semantic concepts, such as actions, usually emerge in the higher layers of the image- and video-language models. We, therefore, propose a layer weighting in the self-attention path to prioritize higher layers. Additionally, we introduce a dynamic weighting method to automatically tune layer weights to capture each layer's relevance to a specific prompt. Finally, we introduce a prompt decomposition, processing action, verb, and object prompts separately, resulting in a better spatial localization of actions. We evaluate the proposed approach on three image- and video-language backbones, CLIP, OpenCLIP, and ViCLIP, and on four video grounding datasets, V-HICO, DALY, YouCook-Interactions, and GroundingYouTube, showing that the proposed training-free approach is able to outperform current trained state-of-the-art approaches for spatial video grounding.

The advancement of Large Vision Language Models (LVLMs) has significantly improved multimodal understanding, yet challenges remain in video reasoning tasks due to the scarcity of high-quality, large-scale datasets. Existing video question-answering (VideoQA) datasets often rely on costly manual annotations with insufficient granularity or automatic construction methods with redundant frame-by-frame analysis, limiting their scalability and effectiveness for complex reasoning. To address these challenges, we introduce VideoEspresso, a novel dataset that features VideoQA pairs preserving essential spatial details and temporal coherence, along with multimodal annotations of intermediate reasoning steps. Our construction pipeline employs a semantic-aware method to reduce redundancy, followed by generating QA pairs using GPT-4o. We further develop video Chain-of-Thought (CoT) annotations to enrich reasoning processes, guiding GPT-4o in extracting logical relationships from QA pairs and video content. To exploit the potential of high-quality VideoQA pairs, we propose a Hybrid LVLMs Collaboration framework, featuring a Frame Selector and a two-stage instruction fine-tuned reasoning LVLM. This framework adaptively selects core frames and performs CoT reasoning using multimodal evidence. Evaluated on our proposed benchmark with 14 tasks against 9 popular LVLMs, our method outperforms existing baselines on most tasks, demonstrating superior video reasoning capabilities. Our code and dataset have been released at: https://github.com/hshjerry/VideoEspresso