English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  DeepCap: Monocular Human Performance Capture Using Weak Supervision

Habermann, M., Xu, W., Zollhöfer, M., Pons-Moll, G., & Theobalt, C. (2020). DeepCap: Monocular Human Performance Capture Using Weak Supervision. Retrieved from https://arxiv.org/abs/2003.08325.

Item is

Basic

show hide
Genre: Paper
Latex : {DeepCap}: {M}onocular Human Performance Capture Using Weak Supervision

Files

show Files
hide Files
:
arXiv:2003.08325.pdf (Preprint), 3MB
Name:
arXiv:2003.08325.pdf
Description:
File downloaded from arXiv at 2021-02-03 07:46
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Habermann, Marc1, Author           
Xu, Weipeng1, Author           
Zollhöfer, Michael2, Author           
Pons-Moll, Gerard3, Author
Theobalt, Christian1, Author           
Affiliations:
1Computer Graphics, MPI for Informatics, Max Planck Society, ou_40047              
2External Organizations, ou_persistent22              
3Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society, ou_persistent22              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV
 Abstract: Human performance capture is a highly important computer vision problem with
many applications in movie production and virtual/augmented reality. Many
previous performance capture approaches either required expensive multi-view
setups or did not recover dense space-time coherent geometry with
frame-to-frame correspondences. We propose a novel deep learning approach for
monocular dense human performance capture. Our method is trained in a weakly
supervised manner based on multi-view supervision completely removing the need
for training data with 3D ground truth annotations. The network architecture is
based on two separate networks that disentangle the task into a pose estimation
and a non-rigid surface deformation step. Extensive qualitative and
quantitative evaluations show that our approach outperforms the state of the
art in terms of quality and robustness.

Details

show
hide
Language(s): eng - English
 Dates: 2020-03-182020
 Publication Status: Published online
 Pages: 12 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 2003.08325
BibTex Citekey: Habermann2003.08325
URI: https://arxiv.org/abs/2003.08325
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show