PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models

TL;DR

PhysRVG introduces a physics-aware reinforcement learning framework for video generation, enforcing physical collision rules directly to improve realism, and extends it with a unified fine-tuning approach called MDcycle, validated on new benchmarks.

Contribution

This work pioneers a physics-aware RL paradigm for video generation, integrating physical collision rules directly into high-dimensional models, and proposes a unified fine-tuning framework called MDcycle.

Findings

Enhanced physical realism in generated videos.

Effective enforcement of collision rules in high-dimensional spaces.

Successful validation on new PhysRVGBench benchmark.

Abstract

Physical principles are fundamental to realistic visual simulation, but remain a significant oversight in transformer-based video generation. This gap highlights a critical limitation in rendering rigid body motion, a core tenet of classical mechanics. While computer graphics and physics-based simulators can easily model such collisions using Newton formulas, modern pretrain-finetune paradigms discard the concept of object rigidity during pixel-level global denoising. Even perfectly correct mathematical constraints are treated as suboptimal solutions (i.e., conditions) during model optimization in post-training, fundamentally limiting the physical realism of generated videos. Motivated by these considerations, we introduce, for the first time, a physics-aware reinforcement learning paradigm for video generation models that enforces physical collision rules directly in high-dimensional spaces, ensuring the physics knowledge is strictly applied rather than treated as conditions. Subsequently, we extend this paradigm to a unified framework, termed Mimicry-Discovery Cycle (MDcycle), which allows substantial fine-tuning while fully preserving the model's ability to leverage physics-grounded feedback. To validate our approach, we construct new benchmark PhysRVGBench and perform extensive qualitative and quantitative experiments to thoroughly assess its effectiveness.