What is it about?
we propose a system “Skeleton2Humanoid” which performs physics-oriented motion correction at test time for motion in-betweening task by regularizing synthesized skeleton motions in a physics simulator. Concretely, our system consists of three sequential stages: (I) test time motion synthesis network adaptation, (II) skeleton to humanoid matching and (III) motion imitation based on reinforcement learning (RL).
Featured Image
Photo by aldi sigun on Unsplash
Why is it important?
Human motion synthesis is a long-standing problem with various applications in digital twins and the Metaverse. However, modern deep learning based motion synthesis approaches barely consider the physical plausibility of synthesized motions and consequently they usually produce unrealistic human motions. We try to solve this by optimizing the synthesized motions at test time and utilize humanoid character to model the physics laws.
Read the Original
This page is a summary of: Skeleton2Humanoid: Animating Simulated Characters for Physically-plausible Motion In-betweening, October 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3503161.3548093.
You can read the full text:
Contributors
The following have contributed to this page
