This repository is for the checkpoint of "MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training"
Abstract: In text-to-motion generation, controllability as well as generation quality and speed has become increasingly critical. The controllability challenges include generating a motion of a length that matches the given textual description and editing the generated motions according to control signals, such as the start-end positions and the pelvis trajectory. In this paper, we propose MoLA, which provides fast, high-quality, variable-length motion generation and can also deal with multiple editing tasks in a single framework. Our approach revisits the motion representation used as inputs and outputs in the model, incorporating an activation variable to enable variable-length motion generation. Additionally, we integrate a variational autoencoder and a latent diffusion model, further enhanced through adversarial training, to achieve high-quality and fast generation. Moreover, we apply a training-free guided generation framework to achieve various editing tasks with motion control inputs. We quantitatively show the effectiveness of adversarial learning in text-to-motion generation, and demonstrate the applicability of our editing framework to multiple editing tasks in the motion domain.
PDF: arXiv
Codebase: Training and inference codes are available at the GitHub
Citation:
@article{uchida2024mola,
title={MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training},
author={Uchida, Kengo and Shibuya, Takashi and Takida, Yuhta and Murata, Naoki and Tanke, Julian and Takahashi, Shusuke and Mitsufuji, Yuki},
journal={arXiv preprint arXiv:2406.01867},
year={2024}
}
License: Code is released under MIT, this checkpoints are released under CC-BY 4.0.