SRPS-deep-learning-based photometric stereo using superresolution images

Euijeong Song, Seokjung Kim, Seok Chung, Minho Chang

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)


This paper introduces a novel deep-learning-based photometric stereo method that uses superresolution (SR) images: SR photometric stereo. Recent deep-learning-based SR algorithms have yielded great results in terms of enlarging images without mosaic effects. Supposing that the SR algorithms successfully enhance the feature and colour information of original images, implementing SR images using the photometric stereo method facilitates the use of considerably more information on the object than existing photometric stereo methods. We built a novel deep-learning-based network for the photometric stereo technique to optimize the input-output of SR image inputs and normal map outputs. We tested our network using the most widely used benchmark dataset and obtained better results than existing photometric stereo methods.

Original languageEnglish
Pages (from-to)995-1012
Number of pages18
JournalJournal of Computational Design and Engineering
Issue number4
Publication statusPublished - 2021 Aug 1

Bibliographical note

Publisher Copyright:
© 2021 The Author(s) 2021. Published by Oxford University Press on behalf of the Society for Computational Design and Engineering.


  • computer vision
  • convolutional neural network
  • deep learning
  • image superresolution
  • photometric stereo

ASJC Scopus subject areas

  • Computational Mechanics
  • Modelling and Simulation
  • Engineering (miscellaneous)
  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design
  • Computational Mathematics


Dive into the research topics of 'SRPS-deep-learning-based photometric stereo using superresolution images'. Together they form a unique fingerprint.

Cite this