technical paper

AAAI 2024

February 24, 2024

Vancouver , Canada

Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations | VIDEO

keywords:

music-conditioned 3d dance generation

reward model

reinforcement learning

This paper presents an Exploratory 3D Dance generation framework, E3D2, designed to address the exploration capability deficiency in existing music-conditioned 3D dance generation models. Current models often generate monotonous and simplistic dance sequences that misalign with human preferences because they lack exploration capabilities.The E3D2 framework involves a reward model trained from automatically-ranked dance demonstrations, which then guides the reinforcement learning process. This approach encourages the agent to explore and generate high quality and diverse dance movement sequences. The soundness of the reward model is both theoretically and experimentally validated. Empirical experiments demonstrate the effectiveness of E3D2 on the AIST++ dataset.

Downloads

SlidesPaperTranscript English (automatic)

Next from AAAI 2024

HISR: Hybrid Implicit Surface Representation for Photorealistic 3D Human Reconstruction
technical paper

HISR: Hybrid Implicit Surface Representation for Photorealistic 3D Human Reconstruction

AAAI 2024

+4Angtian Wang
Angtian Wang and 6 other authors

24 February 2024

Stay up to date with the latest Underline news!

Select topic of interest (you can select more than one)

PRESENTATIONS

  • All Lectures
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2023 Underline - All rights reserved