Deakin University
Browse
DOCUMENT
li-learningtominify-2019.pdf (1.67 MB)
DOCUMENT
li-learningtominify-post-2019.pdf (2.54 MB)
1/0
2 files

Learning to minify photometric stereo

conference contribution
posted on 2019-01-01, 00:00 authored by Junxuan Li, Antonio Robles-KellyAntonio Robles-Kelly, Shaodi You, Yasuyuki Matsushita
Photometric stereo estimates the surface normal given a set of images acquired under different illumination conditions. To deal with diverse factors involved in the image formation process, recent photometric stereo methods demand a large number of images as input. We propose a method that can dramatically decrease the demands on the number of images by learning the most informative ones under different illumination conditions. To this end, we use a deep learning framework to automatically learn the critical illumination conditions required at input. Furthermore, we present an occlusion layer that can synthesize cast shadows, which effectively improves the estimation accuracy. We assess our method on challenging real-world conditions, where we outperform techniques elsewhere in the literature with a significantly reduced number of light conditions.

History

Pagination

7568-7576

Location

Long Beach, California

Open access

  • Yes

Start date

2019-06-16

End date

2019-06-20

ISSN

1063-6919

ISBN-13

9781728132938

Language

eng

Publication classification

E1 Full written paper - refereed

Copyright notice

2019, IEEE

Title of proceedings

CVPR 2019: The IEEE Conference on Computer Vision and Pattern Recognition

Event

Computer Vision and Pattern Recognition. Conference (2019: Long Beach, California)

Publisher

IEEE

Place of publication

Piscataway, N.J.

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC