Demultiplexing Colored Images for Multispectral Photometric Stereo via Deep Neural Networks

Demultiplexing Colored Images for Multispectral Photometric Stereo via Deep Neural Networks

Recovering fine-scale surface shapes is a challenging task in computer vision. Multispectral photometric stereo is one of the popular methods as it can handle non-rigid/moving objects and produces per-pixel dense results. However, the colored images captured by practical multispectral photometric st...

Full description

Bibliographic Details
Main Authors: Yakun Ju, Lin Qi, Huiyu Zhou, Junyu Dong, Liang Lu
Format: Article
Language:English
Published: IEEE 2018-01-01
Series:IEEE Access
Subjects:
Multispectal photometric stereo
spectrum demultiplexing
normal estimation
deep neural networks
Online Access:https://ieeexplore.ieee.org/document/8364553/

Internet

https://ieeexplore.ieee.org/document/8364553/

Similar Items