Physical Simulator In-the-Loop Video Generation

TL;DR

This paper introduces PSIVG, a framework that integrates physical simulation into diffusion-based video generation to produce more physically plausible and coherent videos, addressing limitations of current methods.

Contribution

The paper presents a novel framework combining physical simulation with diffusion models and introduces TTCO for texture consistency, improving physical realism in generated videos.

Findings

Videos exhibit improved physical plausibility and coherence.

Enhanced adherence to real-world physics without sacrificing visual quality.

Framework maintains diversity in generated videos.

Abstract

Recent advances in diffusion-based video generation have achieved remarkable visual realism but still struggle to obey basic physical laws such as gravity, inertia, and collision. Generated objects often move inconsistently across frames, exhibit implausible dynamics, or violate physical constraints, limiting the realism and reliability of AI-generated videos. We address this gap by introducing Physical Simulator In-the-loop Video Generation (PSIVG), a novel framework that integrates a physical simulator into the video diffusion process. Starting from a template video generated by a pre-trained diffusion model, PSIVG reconstructs the 4D scene and foreground object meshes, initializes them within a physical simulator, and generates physically consistent trajectories. These simulated trajectories are then used to guide the video generator toward spatio-temporally physically coherent motion. To further improve texture consistency during object movement, we propose a Test-Time Texture Consistency Optimization (TTCO) technique that adapts text and feature embeddings based on pixel correspondences from the simulator. Comprehensive experiments demonstrate that PSIVG produces videos that better adhere to real-world physics while preserving visual quality and diversity. Project Page: https://vcai.mpi-inf.mpg.de/projects/PSIVG/