Loading...
Loading...

Go to the content (press return)

Multi-view 3D face reconstruction in the wild using siamese networks

Author
Ramon, E.; Escur, J.; Giro, X.
Type of activity
Presentation of work at congresses
Name of edition
2nd 3D Face Alignment in the Wild Challenge
Date of publication
2019
Presentation's date
2019-11-02
Book of congress proceedings
Proceedings of the 2nd 3D Face Alignment in the Wild Challenge
First page
1
Last page
5
Publisher
Computer Vision Foundation
Project funding
Deep learning for 3D Reconstruction and simulation of aesthetic procedures
Multimodal Signal Processing and Machine Learning on Graphs
Repository
http://hdl.handle.net/2117/171469 Open in new window
https://imatge.upc.edu/web/publications/multi-view-3d-face-reconstruction-wild-using-siamese-networks Open in new window
URL
http://openaccess.thecvf.com/ICCV2019_workshops/ICCV2019_3DFAW.py Open in new window
Abstract
In this work, we present a novel learning based approach to reconstruct 3D faces from a single or multiple images. Our method uses a simple yet powerful architecture based on siamese neural networks that helps to extract relevant features from each view while keeping the models small. Instead of minimizing multiple objectives, we propose to simultaneously learn the 3D shape and the individual camera poses by using a single term loss based on the reprojection error, which generalizes from one to ...
Citation
Ramon, E.; Escur, J.; Giro, X. Multi-view 3D face reconstruction in the wild using siamese networks. A: 3D Face Alignment in the Wild Challenge. "Proceedings of the 2nd 3D Face Alignment in the Wild Challenge". Computer Vision Foundation, 2019, p. 1-5.
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

  • Ramon, Eduard  (author and speaker )
  • Escur, Janna  (author and speaker )
  • Giro Nieto, Xavier  (author and speaker )