物理引导人体运动扩散模型

来自今天的爱可可AI前沿推介。

[CV] PhysDiff: Physics-Guided Human Motion Diffusion Model

PhysDiff: 物理引导人体运动扩散模型

简介：提出一种新的运动扩散模型——PhysDiff，将物理约束纳入扩散过程，以产生物理上可信的人体运动。实验表明，PhysDiff可达到SOTA的运动质量，并在物理可信度方面有很大提高。

摘要：去噪扩散模型在生成多样化和真实的人体运动方面有着巨大的前景。然而，现有的运动扩散模型在很大程度上忽视了扩散过程中的物理学规律，往往会产生物理上不可信的运动，并带有明显的假象，如漂浮、脚滑和地面穿透。这严重影响了生成运动的质量，并限制了其在现实世界的应用。为解决该问题，本文提出一种新的物理学指导的运动扩散模型(PhysDiff)，将物理约束纳入了扩散过程。提出基于物理的运动投影模块，该模块用物理模拟器中的运动模仿，将扩散步骤的去噪运动投影到物理上可信的运动。投射的运动在下一个扩散步骤中被进一步使用，以指导去噪扩散过程。在该模型中使用物理学，可以将运动拉向物理上可信的空间。在大规模人体运动数据集上的实验表明，该方法达到了最先进的运动质量，并极大地提高了物理上的可信度(所有数据集的可信度大于78%)。

论文地址：https://arxiv.org/abs/2212.02500

Denoising diffusion models hold great promise for generating diverse and realistic human motions. However, existing motion diffusion models largely disregard the laws of physics in the diffusion process and often generate physically-implausible motions with pronounced artifacts such as floating, foot sliding, and ground penetration. This seriously impacts the quality of generated motions and limits their real-world application. To address this issue, we present a novel physics-guided motion diffusion model (PhysDiff), which incorporates physical constraints into the diffusion process. Specifically, we propose a physics-based motion projection module that uses motion imitation in a physics simulator to project the denoised motion of a diffusion step to a physically-plausible motion. The projected motion is further used in the next diffusion step to guide the denoising diffusion process. Intuitively, the use of physics in our model iteratively pulls the motion toward a physically-plausible space. Experiments on large-scale human motion datasets show that our approach achieves state-of-the-art motion quality and improves physical plausibility drastically (>78% for all datasets).

内容中包含的图片若涉及版权问题，请及时与我们联系删除