Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Model. (arXiv:2210.12315v2 [cs.CV] UPDATED)

We propose a simple and novel method for generating 3D human motion from
complex natural language sentences, which describe different velocity,
direction and composition of all kinds of actions. Different from existing
methods that use classical generative architecture, we apply the Denoising
Diffusion Probabilistic Model to this task, synthesizing diverse motion results
under the guidance of texts. The diffusion model converts white noise into
structured 3D motion by a Markov process with a series of denoising steps and
is efficiently …

apply architecture arxiv denoising diffusion diffusion model diverse generative guidance human language markov natural natural language noise novel probabilistic model process series text white noise