Loading...
Loading...

Go to the content (press return)

Hyperparameter-free losses for model-based monocular reconstruction

Author
Ramon, E.; Ruiz, G.; Batard, T.; Giro, X.
Type of activity
Presentation of work at congresses
Name of edition
4th Geometry Meets Deep Learning Workshop
Date of publication
2019
Presentation's date
2019-11-02
Book of congress proceedings
2019 International Conference on Computer Vision ICCV 2019: proceedings: 27 October - 2 November 2019 Seoul, Korea
First page
1
Last page
10
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Repository
http://hdl.handle.net/2117/179432 Open in new window
https://imatge.upc.edu/web/publications/hyperparameter-free-losses-model-based-monocular-reconstruction Open in new window
URL
http://openaccess.thecvf.com/ICCV2019_workshops/menu.py Open in new window
Abstract
This work proposes novel hyperparameter-free losses for single view 3D reconstruction with morphable models (3DMM). We dispense with the hyperparameters used in other works by exploiting geometry, so that the shape of the object and the camera pose are jointly optimized in a sole term expression. This simplification reduces the optimization time and its complexity. Moreover, we propose a novel implicit regularization technique based on random virtual projections that does not require additional ...
Citation
Ramon, E. [et al.]. Hyperparameter-free losses for model-based monocular reconstruction. A: Geometry Meets Deep Learning Workshop. "2019 International Conference on Computer Vision ICCV 2019: proceedings : 27 October - 2 November 2019 Seoul, Korea". Institute of Electrical and Electronics Engineers (IEEE), 2019, p. 1-10.
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants