Abstract
In this paper we propose the first deep unsupervised approach in human body reconstruction to estimate body surface from a sparse set of landmarks, so called DeepMurf. We apply a denoising autoencoder to estimate missing landmarks. Then we apply an attention model to estimate body joints from landmarks. Finally, a cascading network is applied to regress parameters of a statistical generative model that reconstructs body. Our set of proposed loss functions allows us to train the network in an unsupervised way. Results on four public datasets show that our approach accurately reconstructs the human body from real world mocap data.
Original language | English |
---|---|
Article number | 8 |
Journal | International Journal of Computer Vision |
Volume | 129 |
Issue number | 8 |
Pages (from-to) | 2499-2512 |
Number of pages | 14 |
ISSN | 0920-5691 |
DOIs | |
Publication status | Published - 2021 |
Externally published | Yes |
Bibliographical note
Funding Information:This work is partially supported by ICREA under the ICREA Academia programme, and by the Spanish project PID2019-105093GB-I00 (MINECO/FEDER, UE) and CERCA Programme/Generalitat de Catalunya, and by Amazon Research Awards ARA.
Publisher Copyright:
© 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Keywords
- Attention model
- Cascading
- Human body reconstruction
- Mocap data
- Unsupervised deep learning