Perceiving Systems, Computer Vision

SMPLpix: Neural Avatars from 3D Human Models

2021

Conference Paper

ps


Recent advances in deep generative models have led to an unprecedented level of realism for synthetically generated images of humans. However, one of the remaining fundamental limitations of these models is the ability to flexibly control the generative process, e.g. change the camera and human pose while retaining the subject identity. At the same time, deformable human body models like SMPL \cite{loper2015smpl} and its successors provide full control over pose and shape, but rely on classic computer graphics pipelines for rendering. Such rendering pipelines require explicit mesh rasterization that (a) does not have the potential to fix artifacts or lack of realism in the original 3D geometry and (b) until recently, were not fully incorporated into deep learning frameworks. In this work, we propose to bridge the gap between classic geometry-based rendering and the latest generative networks operating in pixel space. We train a network that directly converts a sparse set of 3D mesh vertices into photorealistic images, alleviating the need for traditional rasterization mechanism. We train our model on a large corpus of human 3D models and corresponding real photos, and show the advantage over conventional differentiable renderers both in terms of the level of photorealism and rendering efficiency.

Author(s): Sergey Prokudin and Michael J. Black and Javier Romero
Book Title: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV 2021)
Pages: 1809--1818
Year: 2021
Month: January
Publisher: IEEE

Department(s): Perceiving Systems
Research Project(s): Neural Rendering
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: 10.1109/WACV48630.2021.00185
Event Name: IEEE Winter Conference on Applications of Computer Vision (WACV 2021)
Event Place: Virtual

Address: Piscataway, NJ
ISBN: 978-1-6654-0477-8
State: Published

Links: project
official pdf
video
preprint
code
Video:

BibTex

@inproceedings{SMPLpix:WACV:2020,
  title = {{SMPLpix}: Neural Avatars from {3D} Human Models},
  author = {Prokudin, Sergey and Black, Michael J. and Romero, Javier},
  booktitle = {2021 IEEE Winter Conference on Applications of Computer Vision (WACV 2021)},
  pages = {1809--1818},
  publisher = {IEEE},
  address = {Piscataway, NJ},
  month = jan,
  year = {2021},
  doi = {10.1109/WACV48630.2021.00185},
  month_numeric = {1}
}