A Novel Joint Points and Silhouette-Based Method to Estimate 3D Human Pose and Shape
(2021) In Lecture Notes in Computer Science 12661. p.41-56- Abstract
- This paper presents a novel method for 3D human pose and shape estimation from images with sparse views, using joint points and silhouettes, based on a parametric model. Firstly, the parametric model is fitted to the joint points estimated by deep learning-based human pose estimation. Then, we extract the correspondence between the parametric model of pose fitting and silhouettes in 2D and 3D space. A novel energy function based on the correspondence is built and minimized to fit a parametric model to the silhouettes. Our approach uses comprehensive shape information because the energy function of silhouettes is built from both 2D and 3D space. This also means that our method only needs images from sparse views, which balances data used... (More)
- This paper presents a novel method for 3D human pose and shape estimation from images with sparse views, using joint points and silhouettes, based on a parametric model. Firstly, the parametric model is fitted to the joint points estimated by deep learning-based human pose estimation. Then, we extract the correspondence between the parametric model of pose fitting and silhouettes in 2D and 3D space. A novel energy function based on the correspondence is built and minimized to fit a parametric model to the silhouettes. Our approach uses comprehensive shape information because the energy function of silhouettes is built from both 2D and 3D space. This also means that our method only needs images from sparse views, which balances data used and the required prior information. Results on synthetic data and real data demonstrate the competitive performance of our approach on pose and shape estimation of the human body. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/2742de9e-8dbe-4b39-ad81-7f2b3d1102dd
- author
- Li, Zhongguo LU ; Heyden, Anders LU and Oskarsson, Magnus LU
- organization
- publishing date
- 2021
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021
- series title
- Lecture Notes in Computer Science
- volume
- 12661
- pages
- 41 - 56
- publisher
- Springer
- external identifiers
-
- scopus:85104343627
- ISSN
- 1611-3349
- ISBN
- 978-3-030-68762-5
- DOI
- 10.1007/978-3-030-68763-2_4
- language
- English
- LU publication?
- yes
- id
- 2742de9e-8dbe-4b39-ad81-7f2b3d1102dd
- date added to LUP
- 2021-04-26 15:16:40
- date last changed
- 2023-12-07 11:16:19
@inproceedings{2742de9e-8dbe-4b39-ad81-7f2b3d1102dd, abstract = {{This paper presents a novel method for 3D human pose and shape estimation from images with sparse views, using joint points and silhouettes, based on a parametric model. Firstly, the parametric model is fitted to the joint points estimated by deep learning-based human pose estimation. Then, we extract the correspondence between the parametric model of pose fitting and silhouettes in 2D and 3D space. A novel energy function based on the correspondence is built and minimized to fit a parametric model to the silhouettes. Our approach uses comprehensive shape information because the energy function of silhouettes is built from both 2D and 3D space. This also means that our method only needs images from sparse views, which balances data used and the required prior information. Results on synthetic data and real data demonstrate the competitive performance of our approach on pose and shape estimation of the human body.}}, author = {{Li, Zhongguo and Heyden, Anders and Oskarsson, Magnus}}, booktitle = {{Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021}}, isbn = {{978-3-030-68762-5}}, issn = {{1611-3349}}, language = {{eng}}, pages = {{41--56}}, publisher = {{Springer}}, series = {{Lecture Notes in Computer Science}}, title = {{A Novel Joint Points and Silhouette-Based Method to Estimate 3D Human Pose and Shape}}, url = {{http://dx.doi.org/10.1007/978-3-030-68763-2_4}}, doi = {{10.1007/978-3-030-68763-2_4}}, volume = {{12661}}, year = {{2021}}, }