Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Qin, Jia
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2504.09413
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910910627446784
author Qin, Jia
author_facet Qin, Jia
contents We propose a two-stage framework for motion in-betweening that combines diffusion-based motion generation with physics-based character adaptation. In Stage 1, a character-agnostic diffusion model synthesizes transitions from sparse keyframes on a canonical skeleton, allowing the same model to generalize across diverse characters. In Stage 2, a reinforcement learning-based controller adapts the canonical motion to the target character's morphology and dynamics, correcting artifacts and enhancing stylistic realism. This design supports scalable motion generation across characters with diverse skeletons without retraining the entire model. Experiments on standard benchmarks and stylized characters demonstrate that our method produces physically plausible, style-consistent motions under sparse and long-range constraints.
format Preprint
id arxiv_https___arxiv_org_abs_2504_09413
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scalable Motion In-betweening via Diffusion and Physics-Based Character Adaptation
Qin, Jia
Graphics
We propose a two-stage framework for motion in-betweening that combines diffusion-based motion generation with physics-based character adaptation. In Stage 1, a character-agnostic diffusion model synthesizes transitions from sparse keyframes on a canonical skeleton, allowing the same model to generalize across diverse characters. In Stage 2, a reinforcement learning-based controller adapts the canonical motion to the target character's morphology and dynamics, correcting artifacts and enhancing stylistic realism. This design supports scalable motion generation across characters with diverse skeletons without retraining the entire model. Experiments on standard benchmarks and stylized characters demonstrate that our method produces physically plausible, style-consistent motions under sparse and long-range constraints.
title Scalable Motion In-betweening via Diffusion and Physics-Based Character Adaptation
topic Graphics
url https://arxiv.org/abs/2504.09413