English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  Generative Model-Based Loss to the Rescue: A Method to Overcome Annotation Errors for Depth-Based Hand Pose Estimation

Wang, J., Mueller, F., Bernard, F., & Theobalt, C. (2020). Generative Model-Based Loss to the Rescue: A Method to Overcome Annotation Errors for Depth-Based Hand Pose Estimation. Retrieved from https://arxiv.org/abs/2007.03073.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/21.11116/0000-0007-E89A-6 Version Permalink: https://hdl.handle.net/21.11116/0000-000E-32E4-8
Genre: Paper
Latex : Generative Model-Based Loss to the Rescue: {A} Method to Overcome Annotation Errors for Depth-Based Hand Pose Estimation

Files

show Files
hide Files
:
arXiv:2007.03073.pdf (Preprint), 2MB
View   Save
File Permalink:
https://hdl.handle.net/21.11116/0000-0007-E89C-4
Name:
arXiv:2007.03073.pdf
Description:
File downloaded from arXiv at 2021-02-08 10:21
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
View
Copyright Date:
-
Copyright Info:
-
License:
http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Locators

show

Creators

show
hide
 Creators:
Wang, Jiayi1, Author           
Mueller, Franziska1, Author           
Bernard, Florian1, Author           
Theobalt, Christian1, Author                 
Affiliations:
1Computer 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 propose to use a model-based generative loss for training hand pose
estimators on depth images based on a volumetric hand model. This additional
loss allows training of a hand pose estimator that accurately infers the entire
set of 21 hand keypoints while only using supervision for 6 easy-to-annotate
keypoints (fingertips and wrist). We show that our partially-supervised method
achieves results that are comparable to those of fully-supervised methods which
enforce articulation consistency. Moreover, for the first time we demonstrate
that such an approach can be used to train on datasets that have erroneous
annotations, i.e. "ground truth" with notable measurement errors, while
obtaining predictions that explain the depth images better than the given
"ground truth".

Details

show
hide
Language(s): eng - English
 Dates: 2020-07-062020
 Publication Status: Published online
 Pages: 8 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 2007.03073
BibTex Citekey: Wang_2007.03073
URI: https://arxiv.org/abs/2007.03073
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show