PhyRPR: Training-Free Physics-Constrained Video Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhao, Yibo, Li, Hengjia, He, Xiaofei, Wu, Boxi
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915728337141760
author Zhao, Yibo
Li, Hengjia
He, Xiaofei
Wu, Boxi
author_facet Zhao, Yibo
Li, Hengjia
He, Xiaofei
Wu, Boxi
contents Recent diffusion-based video generation models can synthesize visually plausible videos, yet they often struggle to satisfy physical constraints. A key reason is that most existing approaches remain single-stage: they entangle high-level physical understanding with low-level visual synthesis, making it hard to generate content that require explicit physical reasoning. To address this limitation, we propose a training-free three-stage pipeline,\textit{PhyRPR}:\textit{Phy\uline{R}eason}--\textit{Phy\uline{P}lan}--\textit{Phy\uline{R}efine}, which decouples physical understanding from visual synthesis. Specifically, \textit{PhyReason} uses a large multimodal model for physical state reasoning and an image generator for keyframe synthesis; \textit{PhyPlan} deterministically synthesizes a controllable coarse motion scaffold; and \textit{PhyRefine} injects this scaffold into diffusion sampling via a latent fusion strategy to refine appearance while preserving the planned dynamics. This staged design enables explicit physical control during generation. Extensive experiments under physics constraints show that our method consistently improves physical plausibility and motion controllability.
format Preprint
id arxiv_https___arxiv_org_abs_2601_09255
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PhyRPR: Training-Free Physics-Constrained Video Generation
Zhao, Yibo
Li, Hengjia
He, Xiaofei
Wu, Boxi
Computer Vision and Pattern Recognition
Recent diffusion-based video generation models can synthesize visually plausible videos, yet they often struggle to satisfy physical constraints. A key reason is that most existing approaches remain single-stage: they entangle high-level physical understanding with low-level visual synthesis, making it hard to generate content that require explicit physical reasoning. To address this limitation, we propose a training-free three-stage pipeline,\textit{PhyRPR}:\textit{Phy\uline{R}eason}--\textit{Phy\uline{P}lan}--\textit{Phy\uline{R}efine}, which decouples physical understanding from visual synthesis. Specifically, \textit{PhyReason} uses a large multimodal model for physical state reasoning and an image generator for keyframe synthesis; \textit{PhyPlan} deterministically synthesizes a controllable coarse motion scaffold; and \textit{PhyRefine} injects this scaffold into diffusion sampling via a latent fusion strategy to refine appearance while preserving the planned dynamics. This staged design enables explicit physical control during generation. Extensive experiments under physics constraints show that our method consistently improves physical plausibility and motion controllability.
title PhyRPR: Training-Free Physics-Constrained Video Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.09255