English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Multi-Garment Net: Learning to Dress 3D People from Images

Bhatnagar, B. L., Tiwari, G., Theobalt, C., & Pons-Moll, G. (in press). Multi-Garment Net: Learning to Dress 3D People from Images. In ICCV 2019. Piscataway, NJ: IEEE.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0004-89E8-C Version Permalink: http://hdl.handle.net/21.11116/0000-0004-89ED-7
Genre: Conference Paper
Latex : Multi-Garment Net: {L}earning to Dress {3D} People from Images

Files

show Files
hide Files
:
arXiv:1908.06903.pdf (Preprint), 7MB
 
File Permalink:
-
Name:
arXiv:1908.06903.pdf
Description:
File downloaded from arXiv at 2019-08-26 13:47
Visibility:
Private
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Bhatnagar, Bharat Lal1, Author              
Tiwari, Garvita1, Author              
Theobalt, Christian2, Author              
Pons-Moll, Gerard1, Author              
Affiliations:
1Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society, ou_1116547              
2Computer Graphics, MPI for Informatics, Max Planck Society, ou_40047              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV
 Abstract: We present Multi-Garment Network (MGN), a method to predict body shape and clothing, layered on top of the SMPL model from a few frames (1-8) of a video. Several experiments demonstrate that this representation allows higher level of control when compared to single mesh or voxel representations of shape. Our model allows to predict garment geometry, relate it to the body shape, and transfer it to new body shapes and poses. To train MGN, we leverage a digital wardrobe containing 712 digital garments in correspondence, obtained with a novel method to register a set of clothing templates to a dataset of real 3D scans of people in different clothing and poses. Garments from the digital wardrobe, or predicted by MGN, can be used to dress any body shape in arbitrary poses. We will make publicly available the digital wardrobe, the MGN model, and code to dress SMPL with the garments.

Details

show
hide
Language(s): eng - English
 Dates: 2019-08-192019-08-202019
 Publication Status: Accepted / In Press
 Pages: International Conference in Computer Vision (ICCV), 2019
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: arXiv: 1908.06903
URI: http://arxiv.org/abs/1908.06903
BibTex Citekey: bhatnagar2019mgn
 Degree: -

Event

show
hide
Title: International Conference on Computer Vision
Place of Event: Seoul, Korea
Start-/End Date: 2019-10-27 - 2019-11-02

Legal Case

show

Project information

show

Source 1

show
hide
Title: ICCV 2019
  Abbreviation : ICCV 2019
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Piscataway, NJ : IEEE
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: -