Learning conditional photometric stereo with high-resolution features

Abstract Photometric stereo aims to reconstruct 3D geometry by recovering the dense surface orientation of a 3D object from multiple images under differing illumination. Traditional methods normally adopt simplified reflectance models to make the surface orientation computable. However, the real ref...

Full description

Bibliographic Details

Main Authors:	Yakun Ju, Yuxin Peng, Muwei Jian, Feng Gao, Junyu Dong
Format:	Artigo
Language:	Inglês
Published:	Tsinghua University Press 2021-10-01
Series:	Computational Visual Media
Subjects:	photometric stereo normal estimation deep neural networks 3D reconstruction
Online Access:	https://doi.org/10.1007/s41095-021-0223-y
Tags:	Add Tag No Tags, Be the first to tag this record!