InterPhys: Physics-aware Human Motion Synthesis in a Dynamic Scene
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 50 of its 59 references that are in the map. First posted on arXiv 1 May 2026.
Builds on
50 of 59 references.
References · 50
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2022Human Motion Diffusion Modelcited by 1,062
- 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 577
- 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
- 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
- 2022TEMOS: Generating diverse human motions from textual descriptionscited by 486
- 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
- 2023MoMask: Generative Masked Modeling of 3D Human Motionscited by 388
- 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 294
- 2022EDGE: Editable Dance Generation From Musiccited by 284
- 2022BEHAVE: Dataset and Method for Tracking Human Object Interactionscited by 246
- 2023Guided Motion Diffusion for Controllable Human Motion Synthesiscited by 221
38 more
- 2022Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memorycited by 210
- 2023Object Motion Guided Human Motion Synthesiscited by 206
- 2021Stochastic Scene-Aware Motion Predictioncited by 203
- 2022Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Modelscited by 188
- 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 181
- 2022HUMANISE: Language-conditioned Human Motion Generation in 3D Scenescited by 156
- 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 137
- 2024Scaling Up Dynamic Human-Scene Interaction Modelingcited by 137
- 2020Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenescited by 135
- 2023Controllable Human-Object Interaction Synthesiscited by 107
- 2023Synthesizing Physical Character-Scene Interactionscited by 102
- 20233D Human Pose Estimation via Intuitive Physicscited by 100
- 2022InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interactioncited by 90
- 2022PoseGPT: Quantization-based 3D Human Motion Generation and Forecastingcited by 78
- 2023TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integrationcited by 76
- 2023PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interactioncited by 72
- 2025InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactionscited by 67
- 2022NeMF: Neural Motion Fields for Kinematic Animationcited by 66
- 2024InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interactioncited by 63
- 2024Human-Object Interaction from Human-Level Instructionscited by 62
- 2023Visibility Aware Human-Object Interaction Tracking from Single RGB Cameracited by 58
- 2023DECO: Dense Estimation of 3D Human-Scene Contact In The Wildcited by 54
- 2025TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenizationcited by 46
- 2023Hierarchical Planning and Control for Box Loco-Manipulationcited by 42
- 2023Detecting Human-Object Contact in Imagescited by 41
- 2023GenZI: Zero-Shot 3D Human-Scene Interaction Generationcited by 40
- 2022Differentiable Dynamics for Articulated 3d Human Motion Reconstructioncited by 38
- 2024HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objectscited by 34
- 2025InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generationcited by 31
- 2022Contact-aware Human Motion Forecastingcited by 27
- 2024PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videoscited by 27
- 2025Guiding Human-Object Interactions with Rich Geometry and Relationscited by 24
- 2024InterTrack: Tracking Human Object Interaction without Object Templatescited by 22
- 2025PICO: Reconstructing 3D People In Contact with Objectscited by 22
- 2024HUMOS: Human Motion Model Conditioned on Body Shapecited by 20
- 2025ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generationcited by 19
- 2025FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidancecited by 9
- 2023Scene-aware Human Motion Forecasting via Mutual Distance Predictioncited by 7
Built on by
Citing papers per year: 2026: 1.
1 paper.