DeMoGen: Decomposing Human Motion with Diffusion Models

Published:Dec 26, 2025 15:06
1 min read
ArXiv

Analysis

This paper introduces DeMoGen, a novel approach to human motion generation that focuses on decomposing complex motions into simpler, reusable components. This is a significant departure from existing methods that primarily focus on forward modeling. The use of an energy-based diffusion model allows for the discovery of motion primitives without requiring ground-truth decomposition, and the proposed training variants further encourage a compositional understanding of motion. The ability to recombine these primitives for novel motion generation is a key contribution, potentially leading to more flexible and diverse motion synthesis. The creation of a text-decomposed dataset is also a valuable contribution to the field.

Reference

DeMoGen's ability to disentangle reusable motion primitives from complex motion sequences and recombine them to generate diverse and novel motions.