PhysCorr: Dual-Reward DPO for Physics-Constrained Text-to-Video Generation with Automated Preference Selection

TL;DR

PhysCorr introduces a physics-aware framework for text-to-video generation that enhances physical realism by modeling, evaluating, and optimizing physical consistency, addressing a key challenge in deploying such models in real-world applications.

Contribution

The paper presents PhysCorr, a novel unified framework with PhysicsRM and PhyDPO for modeling and optimizing physical plausibility in video generation, a significant advancement over prior purely perceptual approaches.

Findings

PhysCorr improves physical realism in generated videos.

The framework maintains high visual fidelity and semantic accuracy.

It is compatible with various video generation models.

Abstract

Recent advances in text-to-video generation have achieved impressive perceptual quality, yet generated content often violates fundamental principles of physical plausibility - manifesting as implausible object dynamics, incoherent interactions, and unrealistic motion patterns. Such failures hinder the deployment of video generation models in embodied AI, robotics, and simulation-intensive domains. To bridge this gap, we propose PhysCorr, a unified framework for modeling, evaluating, and optimizing physical consistency in video generation. Specifically, we introduce PhysicsRM, the first dual-dimensional reward model that quantifies both intra-object stability and inter-object interactions. On this foundation, we develop PhyDPO, a novel direct preference optimization pipeline that leverages contrastive feedback and physics-aware reweighting to guide generation toward physically coherent outputs. Our approach is model-agnostic and scalable, enabling seamless integration into a wide range of video diffusion and transformer-based backbones. Extensive experiments across multiple benchmarks demonstrate that PhysCorr achieves significant improvements in physical realism while preserving visual fidelity and semantic alignment. This work takes a critical step toward physically grounded and trustworthy video generation.