Dichromatic Model Based Highlight Removal via Deep Learning

Chan Ho Lee, Jun Sang Yoo, Jong Ok Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution


The dichromatic model has been popularly used for highlight removal. In this paper, we propose a deep learning network which estimates the dichromatic parameters to achieve the highlight removal. Unlike recent works, we utilize not only spatial but also temporal characteristic. The network structure consists of two subnetworks, and the diffuse dictionary and coefficient matrix are generated through each subnetwork. This model is jointly learned by setting 3 loss functions, which split the diffuse and specular components well. To evaluate the performance of highlight removal, we have the diffuse image that highlight is thoroughly removed by calculating the multiplication with the diffuse dictionary and the diffuse weight in a coefficient matrix. This result shows estimating the dichromatic parameters is well implemented in the proposed deep learning method.

Original languageEnglish
Title of host publicationICTC 2020 - 11th International Conference on ICT Convergence
Subtitle of host publicationData, Network, and AI in the Age of Untact
PublisherIEEE Computer Society
Number of pages3
ISBN (Electronic)9781728167589
Publication statusPublished - 2020 Oct 21
Event11th International Conference on Information and Communication Technology Convergence, ICTC 2020 - Jeju Island, Korea, Republic of
Duration: 2020 Oct 212020 Oct 23

Publication series

NameInternational Conference on ICT Convergence
ISSN (Print)2162-1233
ISSN (Electronic)2162-1241


Conference11th International Conference on Information and Communication Technology Convergence, ICTC 2020
Country/TerritoryKorea, Republic of
CityJeju Island


  • AC light
  • Deep learning
  • Dichromatic model
  • Highlight removal

ASJC Scopus subject areas

  • Information Systems
  • Computer Networks and Communications


Dive into the research topics of 'Dichromatic Model Based Highlight Removal via Deep Learning'. Together they form a unique fingerprint.

Cite this