SimDiff: Simulator-constrained Diffusion Model for Physically Plausible Motion Generation

Akihisa Watanabe, Jiawei Ren, Li Siyao, YICHEN PENG, Erwin Wu, Edgar Simo-Serra

Keywords: diffusion model, motion generation

Abstract: Generating physically plausible human motion is crucial for applications such as character animation and virtual reality. Existing approaches often incorporate a simulator-based motion projection layer to the diffusion process to enforce physical plausibility. However, such a method is computationally expensive due to the sequential nature of the simulator, which prevents parallelization. We show that simulator-based motion projection can be interpreted as a form of guidance—either classifier-based or classifier-free—within the diffusion process. Building on this insight, we propose SimDiff, a Simulator-constrained Diffusion Model that integrates environment parameters (e.g., gravity, wind) directly into the denoising process. By conditioning on these parameters, SimDiff generates physically plausible motions efficiently, without repeated simulator calls at inference, and also provides fine-grained control over different physical coefficients. Moreover, SimDiff successfully generalises to unseen combinations of environmental parameters, demonstrating compositional generalisation.

Primary Area: generative models

Submission Number: 16116