Action-Conditioned 3D Human Motion Synthesis with Transformer VAE

04/12/2021
by   Mathis Petrovich, et al.
0

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. Our code and models will be made available.

READ FULL TEXT

Authors

page 1

page 3

page 8

page 14

07/30/2020

Action2Motion: Conditioned Generation of 3D Human Motions

Action recognition is a relatively established task, where givenan input...
04/25/2022

TEMOS: Generating diverse human motions from textual descriptions

We address the problem of generating diverse 3D human motions from textu...
08/12/2021

Conditional Temporal Variational AutoEncoder for Action Video Prediction

To synthesize a realistic action sequence based on a single human image,...
04/04/2022

HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAE

Studies on the automatic processing of 3D human pose data have flourishe...
03/15/2022

ActFormer: A GAN Transformer Framework towards General Action-Conditioned 3D Human Motion Generation

We present a GAN Transformer framework for general action-conditioned 3D...
06/14/2022

Recurrent Transformer Variational Autoencoders for Multi-Action Motion Synthesis

We consider the problem of synthesizing multi-action human motion sequen...
10/20/2020

Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model

We present a probabilistic framework to generate character animations ba...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.