English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  A Deeper Look into DeepCap

Habermann, M., Xu, W., Zollhöfer, M., Pons-Moll, G., & Theobalt, C. (2023). A Deeper Look into DeepCap. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4), 4009-4002. doi:10.1109/TPAMI.2021.3093553.

Item is

Basic

show hide
Genre: Journal Article
Subtitle : (Invited Paper)

Files

show Files
hide Files
:
arXiv:2111.10563.pdf (Preprint), 14MB
Name:
arXiv:2111.10563.pdf
Description:
File downloaded from arXiv at 2021-11-30 12:46
OA-Status:
Not specified
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

Locators

show

Creators

show
hide
 Creators:
Habermann, Marc1, Author           
Xu, Weipeng2, Author           
Zollhöfer, Michael3, Author           
Pons-Moll, Gerard4, Author                 
Theobalt, Christian1, Author                 
Affiliations:
1Visual Computing and Artificial Intelligence, MPI for Informatics, Max Planck Society, ou_3311330              
2Computer Graphics, MPI for Informatics, Max Planck Society, ou_40047              
3External Organizations, ou_persistent22              
4Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society, ou_1116547              

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. This work is an extended version of
DeepCap where we provide more detailed explanations, comparisons and results as
well as applications.

Details

show
hide
Language(s): eng - English
 Dates: 2021-11-20202020212023
 Publication Status: Issued
 Pages: 14 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: Habermann2111.10563
DOI: 10.1109/TPAMI.2021.3093553
PMID: 34191722
 Degree: -

Event

show

Legal Case

show

Project information

show hide
Project name : 4DRepLy
Grant ID : 770784
Funding program : Horizon 2020 (H2020)
Funding organization : European Commission (EC)

Source 1

show
hide
Title: IEEE Transactions on Pattern Analysis and Machine Intelligence
  Other : IEEE Trans. Pattern Anal. Mach. Intell.
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Piscataway, NJ : IEEE
Pages: - Volume / Issue: 45 (4) Sequence Number: - Start / End Page: 4009 - 4002 Identifier: ISSN: 0162-8828
CoNE: https://pure.mpg.de/cone/journals/resource/954925479551