Synthesizing Physically Plausible Human Motions in 3D Scenes
Liang Pan, Jingbo Wang, Buzhen Huang, Junyu Zhang, Haofan Wang, Xu, Tang, Yangang Wang

TL;DR
This paper introduces a physics-based framework for synthesizing realistic human motions in complex 3D scenes, enabling long-term interactions with multiple objects through decoupled control policies trained in simple environments.
Contribution
It proposes a novel divide-and-conquer approach with reusable controllers for interaction and navigation, allowing application in complex, cluttered scenes.
Findings
Controllers trained in simple environments generalize to complex scenes
Decoupled interaction and navigation improve motion realism
Framework supports long-term, multi-object human-scene interactions
Abstract
We present a physics-based character control framework for synthesizing human-scene interactions. Recent advances adopt physics simulation to mitigate artifacts produced by data-driven kinematic approaches. However, existing physics-based methods mainly focus on single-object environments, resulting in limited applicability in realistic 3D scenes with multi-objects. To address such challenges, we propose a framework that enables physically simulated characters to perform long-term interaction tasks in diverse, cluttered, and unseen 3D scenes. The key idea is to decouple human-scene interactions into two fundamental processes, Interacting and Navigating, which motivates us to construct two reusable Controllers, namely InterCon and NavCon. Specifically, InterCon uses two complementary policies to enable characters to enter or leave the interacting state with a particular object (e.g.,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Pose and Action Recognition · Human Motion and Animation · Generative Adversarial Networks and Image Synthesis
