Image de couverture de livre

PhyVLLM: Physics-Guided Video Language Model with Motion-Appearance Disentanglement

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhan, Yu-Wei, Wang, Xin, Chen, Hong, Feng, Tongtong, Feng, Wei, Wang, Ren, Li, Guangyao, Li, Qing, Zhu, Wenwu
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Multi-weather Cross-view Geo-localization Using Denoising Diffusion Models
par: Feng, Tongtong, et autres
Publié: (2024)

DAM-VSR: Disentanglement of Appearance and Motion for Video Super-Resolution
par: Kong, Zhe, et autres
Publié: (2025)

Self-evolving Embodied AI
par: Feng, Tongtong, et autres
Publié: (2026)

Multi-sentence Video Grounding for Long Video Generation
par: Feng, Wei, et autres
Publié: (2024)

AV-Unified: A Unified Framework for Audio-visual Scene Understanding
par: Li, Guangyao, et autres
Publié: (2026)

Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion Model
par: Zhou, Hang, et autres
Publié: (2024)

Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation
par: Zhai, Yuanhao, et autres
Publié: (2024)

EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon Tasks
par: Feng, Tongtong, et autres
Publié: (2025)

BiTAgent: A Task-Aware Modular Framework for Bidirectional Coupling between Multimodal Large Language Models and World Models
par: Zhan, Yu-Wei, et autres
Publié: (2025)

Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding
par: Chen, Houlun, et autres
Publié: (2026)

SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability
par: Wang, Jiankang, et autres
Publié: (2025)

PhyGile: Physics-Prefix Guided Motion Generation for Agile General Humanoid Motion Tracking
par: Bao, Jiacheng, et autres
Publié: (2026)

DisenStudio: Customized Multi-subject Text-to-Video Generation with Disentangled Spatial Control
par: Chen, Hong, et autres
Publié: (2024)

VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding
par: Chen, Houlun, et autres
Publié: (2024)

LLM4VG: Large Language Models Evaluation for Video Grounding
par: Feng, Wei, et autres
Publié: (2023)

ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video
par: Wang, Boyuan, et autres
Publié: (2026)

PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
par: Huang, Yidong, et autres
Publié: (2026)

"PhyWorldBench": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models
par: Gu, Jing, et autres
Publié: (2025)

Separate Motion from Appearance: Customizing Motion via Customizing Text-to-Video Diffusion Models
par: Liu, Huijie, et autres
Publié: (2025)

Disentangled Geometry and Appearance for Efficient Multi-View Surface Reconstruction and Rendering
par: Zhang, Qitong, et autres
Publié: (2025)

4DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular Video
par: Lyu, Jin, et autres
Publié: (2026)

Zero-to-Hero: Zero-Shot Initialization Empowering Reference-Based Video Appearance Editing
par: Su, Tongtong, et autres
Publié: (2025)

MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling
par: Wang, Haoyu, et autres
Publié: (2025)

PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation
par: Xue, Qiyao, et autres
Publié: (2024)

Make Your Actor Talk: Generalizable and High-Fidelity Lip Sync with Motion and Appearance Disentanglement
par: Yu, Runyi, et autres
Publié: (2024)

FlexEdit: Marrying Free-Shape Masks to VLLM for Flexible Image Editing
par: Yuan, Tianshuo, et autres
Publié: (2024)

VideoPhy: Evaluating Physical Commonsense for Video Generation
par: Bansal, Hritik, et autres
Publié: (2024)

Sign-IDD: Iconicity Disentangled Diffusion for Sign Language Production
par: Tang, Shengeng, et autres
Publié: (2024)

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation
par: Cai, Yuanhao, et autres
Publié: (2025)

Toward Rich Video Human-Motion2D Generation
par: Xi, Ruihao, et autres
Publié: (2025)

Disentangling Foreground and Background Motion for Enhanced Realism in Human Video Generation
par: Liu, Jinlin, et autres
Publié: (2024)

ContPhy: Continuum Physical Concept Learning and Reasoning from Videos
par: Zheng, Zhicheng, et autres
Publié: (2024)

SpectralSplat: Appearance-Disentangled Feed-Forward Gaussian Splatting for Driving Scenes
par: Herau, Quentin, et autres
Publié: (2026)

ResNetVLLM-2: Addressing ResNetVLLM's Multi-Modal Hallucinations
par: Khalil, Ahmad, et autres
Publié: (2025)

MIMAFace: Face Animation via Motion-Identity Modulated Appearance Feature Learning
par: Han, Yue, et autres
Publié: (2024)

PhyRPR: Training-Free Physics-Constrained Video Generation
par: Zhao, Yibo, et autres
Publié: (2026)

Bitrate-Controlled Diffusion for Disentangling Motion and Content in Video
par: Li, Xiao, et autres
Publié: (2025)

PhiP-G: Physics-Guided Text-to-3D Compositional Scene Generation
par: Li, Qixuan, et autres
Publié: (2025)

Pose-Guided Fine-Grained Sign Language Video Generation
par: Shi, Tongkai, et autres
Publié: (2024)

PAM: A Pose-Appearance-Motion Engine for Sim-to-Real HOI Video Generation
par: Gao, Mingju, et autres
Publié: (2026)