Header logo is

Chained Representation Cycling: Learning to Estimate 3D Human Pose and Shape by Cycling Between Representations

2020

Conference Paper

ps


The goal of many computer vision systems is to transform image pixels into 3D representations. Recent popular models use neural networks to regress directly from pixels to 3D object parameters. Such an approach works well when supervision is available, but in problems like human pose and shape estimation, it is difficult to obtain natural images with 3D ground truth. To go one step further, we propose a new architecture that facilitates unsupervised, or lightly supervised, learning. The idea is to break the problem into a series of transformations between increasingly abstract representations. Each step involves a cycle designed to be learnable without annotated training data, and the chain of cycles delivers the final solution. Specifically, we use 2D body part segments as an intermediate representation that contains enough information to be lifted to 3D, and at the same time is simple enough to be learned in an unsupervised way. We demonstrate the method by learning 3D human pose and shape from un-paired and un-annotated images. We also explore varying amounts of paired data and show that cycling greatly alleviates the need for paired data. While we present results for modeling humans, our formulation is general and can be applied to other vision problems.

Author(s): Nadine Rueegg and Christoph Lassner and Michael J. Black and Konrad Schindler
Book Title: The Thirty-Fourth AAAI Conference on Artificial Intelligence
Volume: 4
Pages: 5561--5569
Year: 2020
Month: February
Publisher: AAAI Press

Department(s): Perceiving Systems
Research Project(s): Regressing Humans
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: 10.1609/aaai.v34i04.6008
Event Name: Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020)
Event Place: New York, NY

Address: Palo Alto, CA
ISBN: 978-1-57735-835-0
State: Published

Links: pdf

BibTex

@inproceedings{Ruegg:AAAI:2020,
  title = {Chained Representation Cycling: Learning to Estimate 3D Human Pose and Shape by Cycling Between Representations},
  author = {Rueegg, Nadine and Lassner, Christoph and Black, Michael J. and Schindler, Konrad},
  booktitle = {The Thirty-Fourth AAAI Conference on Artificial Intelligence},
  volume = {4},
  pages = {5561--5569},
  publisher = {AAAI Press},
  address = {Palo Alto, CA},
  month = feb,
  year = {2020},
  doi = {10.1609/aaai.v34i04.6008},
  month_numeric = {2}
}