Imagen de Portada

PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ji, Sihui, Chen, Xi, Tao, Xin, Wan, Pengfei, Zhao, Hengshuang
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives
por: Ji, Sihui, et al.
Publicado: (2025)

LayerFlow: A Unified Model for Layer-aware Video Generation
por: Ji, Sihui, et al.
Publicado: (2025)

VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control
por: Tu, Yuanpeng, et al.
Publicado: (2025)

FashionComposer: Compositional Fashion Image Generation
por: Ji, Sihui, et al.
Publicado: (2024)

StyleMaster: Stylize Your Video with Artistic Generation and Translation
por: Ye, Zixuan, et al.
Publicado: (2024)

3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation
por: Fu, Xiao, et al.
Publicado: (2024)

DiffDoctor: Diagnosing Image Diffusion Models Before Treating
por: Wang, Yiyang, et al.
Publicado: (2025)

PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models
por: Zhang, Qiyuan, et al.
Publicado: (2026)

CamCloneMaster: Enabling Reference-based Camera Control for Video Generation
por: Luo, Yawen, et al.
Publicado: (2025)

FocalClick-XL: Towards Unified and High-quality Interactive Segmentation
por: Chen, Xi, et al.
Publicado: (2025)

MultiShotMaster: A Controllable Multi-Shot Video Generation Framework
por: Wang, Qinghe, et al.
Publicado: (2025)

SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
por: Bai, Jianhong, et al.
Publicado: (2024)

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
por: Bai, Jianhong, et al.
Publicado: (2025)

CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation
por: Wang, Qinghe, et al.
Publicado: (2025)

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation
por: Wang, Chen, et al.
Publicado: (2025)

RelightMaster: Precise Video Relighting with Multi-plane Light Images
por: Bian, Weikang, et al.
Publicado: (2025)

OrthoPhys: Physically Plausible Video Generation with Orthogonal-View Geometry Guidance
por: Wang, Cong, et al.
Publicado: (2026)

PhysFlow: Unleashing the Potential of Multi-modal Foundation Models and Video Diffusion for 4D Dynamic Physical Scene Simulation
por: Liu, Zhuoman, et al.
Publicado: (2024)

PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding
por: Zhang, Haoze, et al.
Publicado: (2025)

FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation
por: Huang, Kaiyi, et al.
Publicado: (2025)

ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models
por: Xue, Haotian, et al.
Publicado: (2026)

ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning
por: Huang, Yuzhou, et al.
Publicado: (2025)

PhysAlign: Physics-Coherent Image-to-Video Generation through Feature and 3D Representation Alignment
por: Xiong, Zhexiao, et al.
Publicado: (2026)

Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection
por: Ding, Kaixin, et al.
Publicado: (2025)

Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning
por: Lin, Wang, et al.
Publicado: (2025)

LogoSticker: Inserting Logos into Diffusion Models for Customized Generation
por: Zhu, Mingkang, et al.
Publicado: (2024)

TempoMaster: Efficient Long Video Generation via Next-Frame-Rate Prediction
por: Ma, Yukuo, et al.
Publicado: (2025)

ResMaster: Mastering High-Resolution Image Generation via Structural and Fine-Grained Guidance
por: Shi, Shuwei, et al.
Publicado: (2024)

Training-Free Efficient Video Generation via Dynamic Token Carving
por: Zhang, Yuechen, et al.
Publicado: (2025)

Improving Domain Generalization on Gaze Estimation via Branch-out Auxiliary Regularization
por: Zhao, Ruijie, et al.
Publicado: (2024)

CalliMaster: Mastering Page-level Chinese Calligraphy via Layout-guided Spatial Planning
por: Xu, Tianshuo, et al.
Publicado: (2026)

SyncVIS: Synchronized Video Instance Segmentation
por: Zheng, Rongkun, et al.
Publicado: (2024)

MotionMaster: Training-free Camera Motion Transfer For Video Generation
por: Hu, Teng, et al.
Publicado: (2024)

BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation
por: Wang, Ruotong, et al.
Publicado: (2025)

PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos
por: Cao, Meng, et al.
Publicado: (2024)

ViLLa: Video Reasoning Segmentation with Large Language Model
por: Zheng, Rongkun, et al.
Publicado: (2024)

UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation
por: Huang, Jiehui, et al.
Publicado: (2025)

FacePhys: State of the Heart Learning
por: Wang, Kegang, et al.
Publicado: (2025)

VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning
por: Qi, Zhangyang, et al.
Publicado: (2025)

VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning
por: Tan, Hao, et al.
Publicado: (2026)