CVPR 2025 论文列表

In this paper, we present HomoGen, an enhanced video inpainting method based on homography propagation and diffusion models. HomoGen leverages homography registration to propagate contextual pixels as priors for generating missing content in corrupted videos. Unlike previous flow-based propagation methods, which introduce local distortions due to point-to-point optical flows, homography-induced artifacts are typically global structural distortions that preserve semantic integrity. To effectively utilize these priors for generation, we employ a video diffusion model that inherently prioritizes semantic information within the priors over pixel-level details. A content-adaptive control mechanism is proposed to scale and inject the priors into intermediate video latents during iterative denoising. In contrast to existing transformer-based networks that often suffer from artifacts within priors, leading to error accumulation and unrealistic results, our denoising diffusion network can smooth out artifacts and ensure natural outputs. Extensive experiments demonstrate the effectiveness of the proposed method qualitatively and quantitatively.

How can we enable models to comprehend video anomalies occurring over varying temporal scales and contexts?Traditional Video Anomaly Understanding (VAU) methods focus on frame-level anomaly prediction, often missing the interpretability of complex and diverse real-world anomalies. Recent multimodal approaches leverage visual and textual data but lack hierarchical annotations that capture both short-term and long-term anomalies.To address this challenge, we introduce HIVAU-70k, a large-scale benchmark for hierarchical video anomaly understanding across any granularity. We develop a semi-automated annotation engine that efficiently scales high-quality annotations by combining manual video segmentation with recursive free-text annotation using large language models (LLMs). This results in over 70,000 multi-granular annotations organized at clip-level, event-level, and video-level segments.For efficient anomaly detection in long videos, we propose the Anomaly-focused Temporal Sampler (ATS). ATS integrates an anomaly scorer with a density-aware sampler to adaptively select frames based on anomaly scores, ensuring that the multimodal LLM concentrates on anomaly-rich regions, which significantly enhances both efficiency and accuracy.Extensive experiments demonstrate that our hierarchical instruction data markedly improves anomaly comprehension. The integrated ATS and visual-language model outperform traditional methods in processing long videos.Our benchmark and model will be publicly available.

Relightable portrait animation aims to animate a static reference portrait to match the head movements of a driving video while adapting to user-specified or reference lighting conditions. Existing portrait animation methods fail to achieve relightable portraits because they do not separate and manipulate intrinsic (identity and appearance) and extrinsic (pose and lighting) features. In this paper, we present a Lighting Controllable Video Diffusion model (LCVD) for high-fidelity, relightable portrait animation. We address this limitation by distinguishing these feature types through dedicated subspaces within the feature space of a pre-trained image-to-video diffusion model. Specifically, for each frame, we use the 3D mesh of the reference portrait, the pose of the driving frame as well as the specified lighting to render an image called shading hint. While the reference image represents the intrinsic attributes, the shading hint encodes the extrinsic attributes. In the training phase, we employ a reference adapter to map the reference into an intrinsic feature subspace and a shading adapter to map the shading hints into an extrinsic feature subspace. By merging features from these subspaces, the model achieves nuanced control over lighting and pose in generated animations. Extensive evaluations show that LCVD outperforms state-of-the-art methods in lighting realism, image quality, and video consistency, setting a new benchmark in relightable portrait animation. Our project is available at \href https://github.com/MingtaoGuo/Relightable-Portrait-Animation https://github.com/MingtaoGuo/Relightable-Portrait-Animation

Recently, learned video compression (LVC) is undergoing a period of rapid development. However, due to absence of large and high-quality high dynamic range (HDR) video training data, LVC on HDR video is still unexplored. In this paper, we are the first to collect a large-scale HDR video benchmark dataset, named HDRVD2K, featuring huge quantity, diverse scenes and multiple motion types. HDRVD2K fills gaps of video training data and facilitate the development of LVC on HDR videos. Based on HDRVD2K, we further propose the first learned bit-depth scalable video compression (LBSVC) network for HDR videos by effectively exploiting bit-depth redundancy between videos of multiple dynamic ranges. To achieve this, we first propose a compression-friendly bit-depth enhancement module (BEM) to effectively predict original HDR videos based on compressed tone-mapped low dynamic range (LDR) videos and dynamic range prior, instead of reducing redundancy only through spatio-temporal predictions. Our method greatly improves the reconstruction quality and compression performance on HDR videos. Extensive experiments demonstrate the effectiveness of HDRVD2K on learned HDR video compression and great compression performance of our proposed LBSVC network.

Despite advancements in multimodal large language models (MLLMs), current approaches struggle in medium-to-long video understanding due to frame and context length limitations. As a result, these models often depend on frame sampling, which risks missing key information over time and lacks task-specific relevance. To address these challenges, we introduce **HierarQ**, a task-aware hierarchical Q-Former based framework that sequentially processes frames to bypass the need for frame sampling, while avoiding LLM's context length limitations. We introduce a lightweight two-stream language-guided feature modulator to incorporate task awareness in video understanding, with the entity stream capturing frame-level object information within a short context and the scene stream identifying their broader interactions over longer period of time. Each stream is supported by dedicated memory banks which enables our proposed **Hierar**chical **Q**uerying transformer (HierarQ) to effectively capture short and long-term context. Extensive evaluations on **10** video benchmarks across video understanding, question answering, and captioning tasks demonstrate HierarQ's state-of-the-art performance across most datasets, proving its robustness and efficiency for comprehensive video analysis. All code will be made available upon acceptance.

Skeleton-based human action recognition has received widespread attention in recent years due to its diverse range of application scenarios. Due to the different sources of human skeletons, skeleton data naturally exhibit heterogeneity. The previous works, however, overlook the heterogeneity of human skeletons and solely construct models tailored for homogeneous skeletons. This work addresses the challenge of heterogeneous skeleton-based action representation learning, specifically focusing on processing skeleton data that varies in joint dimensions and topological structures. The proposed framework comprises two primary components: heterogeneous skeleton processing and unified representation learning. The former first converts two-dimensional skeleton data into three-dimensional skeleton via an auxiliary network, and then constructs a prompted unified skeleton using skeleton-specific prompts. We also design an additional modality named semantic motion encoding to harness the semantic information within skeletons. The latter module learns a unified action representation using a shared backbone network that processes different heterogeneous skeletons. Extensive experiments on the NTU-60, NTU-120, and PKU-MMD II datasets demonstrate the effectiveness of our method in various tasks of action understanding. Our approach can be applied to action recognition in robots with different humanoid structures.

Currently, the demand for higher video quality has grown significantly. However, satellite video has low resolution, complex motion, and weak textures. Haze interference further exacerbates the loss of motion information and texture details, hindering effective spatiotemporal feature fusion and fine-grained feature mining. This presents significant challenges for subsequent super-resolution (SR) reconstruction, especially at continuous scales. To address these problems, this paper models the double-degradation process of hazy low-quality satellite videos and proposes a novel network to learn the optimal joint degradation pattern (ODPNet) for continuous-scale SR of hazy satellite videos. First, we design a prior-based feature soft dehazing module to eliminate haze interference at the feature level. Second, we develop a spatiotemporal self-attention (SSA) to capture long-range feature dependencies, thereby achieving effective spatiotemporal feature fusion. Third, we devise a tri-branch cross-aggregation block (TCB) to enhance feature representations of weak textures in satellite videos by effectively aggregating contextual information. Finally, we propose a cross-scale feature Top-k selection Transformer (CFTST), which aims to adaptively select and aggregate cross-scale latent codes to learn feature representations of satellite videos at arbitrary resolutions, thus enabling continuous-scale SR. Experiments show that ODPNet outperforms existing methods and achieves a better balance between model parameters and performance.

This paper introduces HarmonySet, a comprehensive dataset designed to advance video-music understanding. HarmonySet consists of 48,328 diverse video-music pairs, annotated with detailed information on rhythmic synchronization, emotional alignment, thematic coherence, and cultural relevance. We propose a multi-step human-machine collaborative framework for efficient annotation, combining human insights with machine-generated descriptions to identify key transitions and assess alignment across multiple dimensions. Additionally, we introduce a novel evaluation framework with tasks and metrics to assess the multi-dimensional alignment of video and music, including rhythm, emotion, theme, and cultural context. Our extensive experiments demonstrate that HarmonySet, along with the proposed evaluation framework, significantly improves the ability of multimodal models to capture and analyze the intricate relationships between video and music. Project page: https://harmonyset.github.io/.

This work aims to reconstruct the 3D geometry of a rigid object manipulated by one or both hands using monocular RGB video. Previous methods rely on Structure-from-Motion or hand priors to estimate relative motion between the object and camera, which typically assume textured objects or single-hand interactions. To accurately recover object geometry in dynamic interactions, we incorporate priors from 3D generation model into object pose estimation and propose semantic consistency constraints to solve the challenge of shape and texture discrepancy between the generated priors and observations. The poses are initialized, followed by joint optimization of the object poses and implicit neural representation. During optimization, a novel pose outlier voting strategy with inter-view consistency is proposed to correct large pose errors. Experiments on three datasets demonstrate that our method significantly outperforms the state-of-the-art in reconstruction quality for both single- and two-hand scenarios. Our project page: https://east-j.github.io/dynhor/

Motivated by the efficiency of spherical harmonics (SH) in representing various physical phenomena, we propose a Holistic panoramic 3D scene Understanding framework using Spherical Harmonics, dubbed as HUSH. Our approach focuses on a unified framework adaptable to various 3D scene understanding tasks via SH bases. To achieve this, we first estimate SH coefficients, allowing for the adaptive configuration of the SH bases specific to each scene. HUSH then employs a hierarchical attention module that uses SH bases as queries to generate comprehensive scene features by integrating these scene-adaptive SH bases with image features. Additionally, we introduce an SH basis index module that adaptively emphasizes relevant SH bases to produce task-relevant features, enhancing the versatility of HUSH across different scene understanding tasks. Finally, by combining the scene features with task-relevant features in the task-specific heads, we perform various scene understanding tasks, including depth, surface normal and room layout estimation. Experiments demonstrate that HUSH achieves state-of-the-art performance on depth estimation benchmarks, highlighting the robustness and scalability of using SH in panoramic 3D scene understanding.

We present a validation dataset of newly-collected kitchen based egocentric videos, manually annotated with highly detailed and interconnected ground-truth labels covering: recipe steps, fine-grained actions, ingredients with nutritional values, moving objects, and audio annotations. Importantly, all annotations are grounded in 3D through digital twinning of the scene, fixtures, object locations, and primed with gaze. Footage is collected from unscripted recordings in diverse home environments, making HD-EPIC the first dataset collected in-the-wild but with detailed annotations matching those in controlled lab environments. We show the potential of our highly-detailed annotations through a challenging VQA benchmark of 26K questions assessing capability to recognise recipes, ingredients, nutrition, fine-grained actions, 3D perception, object motion, and gaze direction. The powerful long-context Gemini Pro only achieves 37.0% on this benchmark, showcasing its difficulty and highlighting shortcomings in current VLMs. We additionally assess action recognition, sound recognition, and long-term video-object segmentation on HD-EPIC. HD-EPIC is 41 hours of video in 9 kitchens with digital twins of 404 kitchen fixtures, capturing 69 recipes, 59K fine-grained actions, 51K audio events, 20K object movements and 37K object masks lifted to 3D. On average, we have 263 annotations per min of our unscripted videos.

Multimodal Language Learning Models (MLLMs) have shown remarkable performance in image understanding, generation, and editing, with recent advancements achieving pixel-level grounding with reasoning. However, these models for common objects struggle with fine-grained face understanding. In this work, we introduce the FacePlayGround-240K dataset, the first pioneering large-scale, pixel-grounded face caption and question-answer (QA) dataset, meticulously curated for alignment pretraining and instruction-tuning. We present the GroundingFace framework, specifically designed to enhance fine-grained face understanding. This framework significantly augments the capabilities of existing grounding models in face part segmentation, face attribute comprehension, while preserving general scene understanding. Comprehensive experiments validate that our approach surpasses current state-of-the-art models in pixel-grounded face captioning/QA and various downstream tasks, including face captioning, referring segmentation, and zero-shot face attribute recognition.

Generative modeling aims to transform random noise into structured outputs. In this work, we enhance video diffusion models by allowing motion control via structured latent noise sampling. This is achieved by just a change in data: we pre-process training videos to yield structured noise. Consequently, our method is agnostic to diffusion model design, requiring no changes to model architectures or training pipelines. Specifically, we propose a novel noise warping algorithm, fast enough to run in real time, that replaces random temporal Gaussianity with correlated warped noise derived from optical flow fields, while preserving the spatial Gaussianity. The efficiency of our algorithm enables us to fine-tune modern video diffusion base models using warped noise with minimal overhead, and provide a one-stop solution for a wide range of user-friendly motion control: local object motion control, global camera movement control, and motion transfer. The harmonization between temporal coherence and spatial Gaussianity in our warped noise leads to effective motion control while maintaining per-frame pixel quality. Extensive experiments and user studies demonstrate the advantages of our method, making it a robust and scalable approach for controlling motion in video diffusion models. Please see our project webpage: https://eyeline-research.github.io/Go-with-the-Flow/ ; source code and checkpoints are available on GitHub: https://github.com/Eyeline-Research/Go-with-the-Flow

3-Dimensional Embodied Reference Understanding (3DERU) combines a language description and an accompanying pointing gesture to identify the most relevant target object in a 3D scene. Although prior work has explored pure language-based 3D grounding, there has been limited exploration of 3D-ERU, which also incorporates human pointing gestures. To address this gap, we introduce a data augmentation framework-Imputer, and use it to curate a new benchmark dataset-ImputeRefer for 3D-ERU, by incorporating human pointing gestures into existing 3D scene datasets that only contain language instructions. We also propose Ges3ViG, a novel model for 3D-ERU that achieves 30% improvement in accuracy as compared to other 3DERU models and 9% compared to other purely language-based 3D grounding models. Our code and dataset are available at https://github.com/AtharvMane/Ges3ViG.

We introduce a novel geometry-guided online video view synthesis method with enhanced view and temporal consistency. Traditional approaches achieve high-quality synthesis from dense multi-view camera setups but require significant computational resources. In contrast, selective-input methods reduce this cost but often compromise quality, leading to multi-view and temporal inconsistencies such as flickering artifacts. Our method addresses this challenge to deliver efficient, high-quality novel-view synthesis with view and temporal consistency. The key innovation of our approach lies in using global geometry to guide an image-based rendering pipeline. To accomplish this, we progressively refine depth maps using color difference masks across time. These depth maps are then accumulated through truncated signed distance fields in the synthesized view's image space. This depth representation is view and temporally consistent, and is used to guide a pre-trained blending network that fuses multiple forward-rendered input-view images. Thus, the network is encouraged to output geometrically consistent synthesis results across multiple views and time. Our approach achieves consistent, high-quality video synthesis, while running efficiently in an online manner.

Large-scale video generation models have the inherent ability to realistically model natural scenes. In this paper, we demonstrate that through a careful design of a generative video propagation framework, various video tasks can be addressed in a unified way by leveraging the generative power of such models. Specifically, our framework, GenProp, encodes the original video with a selective content encoder and propagates the changes made to the first frame using an image-to-video generation model. We propose a data generation scheme to cover multiple video tasks based on instance-level video segmentation datasets. Our model is trained by incorporating a mask prediction decoder head and optimizing a region-aware loss to aid the encoder to preserve the original content while the generation model propagates the modified region. This novel design opens up new possibilities: In editing scenarios, GenProp allows substantial changes to an object's shape; for insertion, the inserted objects can exhibit independent motion; for removal, GenProp effectively removes effects like shadows and reflections from the whole video; for tracking, GenProp is capable of tracking objects and their associated effects together. Experiment results demonstrate the leading performance of our model in various video tasks, and we further provide in-depth analyses of the proposed framework.

Given a video and a set of input object masks, an omnimatte method aims to decompose the video into semantically meaningful layers containing individual objects along with their associated effects, such as shadows and reflections.Existing omnimatte methods assume a static background or accurate pose and depth estimation and produce poor decompositions when these assumptions are violated. Furthermore, due to the lack of generative prior on natural videos, existing methods cannot complete dynamic occluded regions.We present a novel generative layered video decomposition framework to address the omnimatte problem. Our method does not assume a stationary scene or require camera pose or depth information and produces clean, complete layers, including convincing completions of occluded dynamic regions. Our core idea is to train a video diffusion model to identify and remove scene effects caused by a specific object. We show that this model can be finetuned from an existing video inpainting model with a small, carefully curated dataset, anddemonstrate high-quality decompositions and editing results for a wide range of casually captured videos containing soft shadows, glossy reflections, splashing water, and more.

We address the problem of generating videos from unposed internet photos. A handful of input images serve as keyframes, and our model interpolates between them to simulate a path moving between the cameras. Given random images, a model's ability to capture underlying geometry, recognize scene identity, and relate frames in terms of camera position and orientation reflects a fundamental understanding of 3D structure and scene layout. However, existing video models such as Luma Dream Machine fail at this task. We design a self-supervised method that takes advantage of the consistency of videos and variability of multiview internet photos to train a scalable, 3D-aware video model without any 3D annotations such as camera parameters. We validate that our method outperforms commercial models in terms of geometric and appearance consistency. We also show our model benefits applications that enable camera control, such as 3D Gaussian Splatting. Our results suggest that we can scale up scene-level 3D learning using only 2D data such as videos and multiview internet photos.

Three key challenges hinder the development of current deepfake video detection: (1) Temporal features can be complex and diverse: how can we identify general temporal artifacts to enhance model generalization? (2) Spatiotemporal models often lean heavily on one type of artifact and ignore the other: how can we ensure balanced learning from both? (3) Videos are naturally resource-intensive: how can we tackle efficiency without compromising accuracy? This paper attempts to tackle the three challenges jointly. First, inspired by the notable generality of using image-level blending data for image forgery detection, we investigate whether and how video-level blending can be effective in video. We then perform a thorough analysis and identify a previously underexplored temporal forgery artifact: Facial Feature Drift (FFD), which commonly exists across different forgeries. To reproduce FFD, we then propose a novel Video-level Blending data (VB), where VB is implemented by blending the original image and its warped version frame-by-frame, serving as a hard negative sample to mine more general artifacts. Second, we carefully design a lightweight Spatiotemporal Adapter (StA) to equip a pre-trained image model with the ability to capture both spatial and temporal features jointly and efficiently. StA is designed with two-stream 3D-Conv with varying kernel sizes, allowing it to process spatial and temporal features separately. This eliminates the need to design a new deepfake-specific video architecture from scratch. Extensive experiments validate the effectiveness of the proposed methods; and show our approach can generalize well to previously unseen forgery videos.