TEMOS: Generating diverse human motions from textual descriptions
This addresses the problem of creating varied human animations from text for applications in animation and robotics, though it is incremental as it builds on prior motion generation work.
The paper tackles generating diverse 3D human motions from text by proposing TEMOS, a variational model that produces multiple motions instead of a single deterministic one, showing significant improvements on the KIT Motion-Language benchmark.
We address the problem of generating diverse 3D human motions from textual descriptions. This challenging task requires joint modeling of both modalities: understanding and extracting useful human-centric information from the text, and then generating plausible and realistic sequences of human poses. In contrast to most previous work which focuses on generating a single, deterministic, motion from a textual description, we design a variational approach that can produce multiple diverse human motions. We propose TEMOS, a text-conditioned generative model leveraging variational autoencoder (VAE) training with human motion data, in combination with a text encoder that produces distribution parameters compatible with the VAE latent space. We show the TEMOS framework can produce both skeleton-based animations as in prior work, as well more expressive SMPL body motions. We evaluate our approach on the KIT Motion-Language benchmark and, despite being relatively straightforward, demonstrate significant improvements over the state of the art. Code and models are available on our webpage.