Action-Conditioned 3D Human Motion Synthesis with Transformer VAE
Authors:
Top Cited Papers
- 1 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 10965-10975
Abstract
We tackle the problem of action-conditioned generation of realistic and diverse human motion sequences. In contrast to methods that complete, or extend, motion sequences, this task does not require an initial pose or sequence. Here we learn an action-aware latent representation for human motions by training a generative variational autoencoder (VAE). By sampling from this latent space and querying a certain duration through a series of positional encodings, we synthesize variable-length motion sequences conditioned on a categorical action. Specifically, we design a Transformer-based architecture, ACTOR, for encoding and decoding a sequence of parametric SMPL human body models estimated from action recognition datasets. We evaluate our approach on the NTU RGB+D, HumanAct12 and UESTC datasets and show improvements over the state of the art. Furthermore, we present two use cases: improving action recognition through adding our synthesized data to training, and motion denoising. Code and models are available on our project page [53].Keywords
All Related Versions
This publication has 46 references indexed in Scilit:
- Phase-functioned neural networks for character controlACM Transactions on Graphics, 2017
- A deep learning framework for character motion synthesis and editingACM Transactions on Graphics, 2016
- NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis2016
- Recurrent Network Models for Human Dynamics2015
- SMPLACM Transactions on Graphics, 2015
- Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural EnvironmentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Latent structured models for human pose estimation2011
- Modeling Human Locomotion with Topologically Constrained Latent Variable Models2007
- Learning Variable-Length Markov Models of BehaviorComputer Vision and Image Understanding, 2001
- The Visual Analysis of Human Movement: A SurveyComputer Vision and Image Understanding, 1999