InterPhys: Physics-aware Human Motion Synthesis in a Dynamic Scene
Chaoyue Xing, Wei Mao, Miaomiao Liu
Abstract
This paper tackles the problem of physics-aware human motion synthesis in a dynamic scene. Unlike existing works which mainly tend to generate physically unrealistic motions due to limited contact modeling, typically restricted to hands, in this paper, we introduce a physics-aware human motion generation framework that explicitly models the full spectrum of human-related forces, including human-object, human-scene, and internal body dynamics. Our method imposes soft physical constraints to maintain force and torque balance, ensuring physically grounded motion synthesis. We further propose a novel continuous distance-based force model that generalizes contact modeling to arbitrary surfaces, capturing interactions not only with static environments but also with dynamic, moving objects. Extensive experiments show that our approach significantly improves physical plausibility and generalizes well to complex scenes, setting a new benchmark for physically consistent human motion generation.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 3d1b96ad-6f1a-498a-b0f1-13fe735c14d3Builds on36
- AI Choreographer: Music Conditioned 3D Dance Generation with AIST++Ruilong Li, Shan Yang, David A. Ross, Angjoo KanazawaICCV 2021 · 701 citations
- Action-Conditioned 3D Human Motion Synthesis with Transformer VAEMathis Petrovich, Michael J. Black, Gül VarolICCV 2021 · 672 citations
- Generating Diverse and Natural 3D Human Motions from TextChuan Guo, Shihao Zou, Xinxin Zuo, Sen Wang et al.CVPR 2022 · 462 citations
- Resolving 3D Human Pose Ambiguities With 3D Scene ConstraintsMohamed Hassan, Vasileios Choutas, Dimitrios Tzionas, Michael J. BlackICCV 2019 · 384 citations
- Guided Motion Diffusion for Controllable Human Motion SynthesisKorrawe Karunratanakul, Konpat Preechakul, Supasorn Suwajanakorn, Siyu TangICCV 2023 · 240 citations
Related papers
- Contact-aware Human Motion ForecastingWei Mao, Miaomiao Liu, Richard I. Hartley, Mathieu SalzmannNeurIPS 2022 · 43 citations
- Synthesizing Long-Term 3D Human Motion and Interaction in 3D ScenesJiashun Wang, Huazhe Xu, Jingwei Xu, Sifei Liu et al.CVPR 2021
- Scene-Aware Generative Network for Human Motion SynthesisJingbo Wang, Sijie Yan, Bo Dai, Dahua LinCVPR 2021
- Physics-based Human Motion Estimation and Synthesis from VideosKevin Xie, Tingwu Wang, Umar Iqbal, Yunrong Guo et al.ICCV 2021 · 102 citations
- PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular VideosYufei Zhang, Jeffrey O. Kephart, Zijun Cui, Qiang JiCVPR 2024 · 14 citations
