Temporally Consistent Relighting for Portrait Videos

Sreenithy Chandran, Yannick Hold-Geoffroy, Kalyan Sunkavalli, Zhixin Shu, Suren Jayasuriya

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

2 Scopus citations

Abstract

Ensuring ideal lighting when recording videos of people can be a daunting task requiring a controlled environment and expensive equipment. Methods were recently proposed to perform portrait relighting for still images, enabling after-the-fact lighting enhancement. However, naively applying these methods on each frame independently yields videos plagued with flickering artifacts. In this work, we propose the first method to perform temporally consistent video portrait relighting. To achieve this, our method optimizes end-to-end both desired lighting and temporal consistency jointly. We do not require ground truth lighting annotations during training, allowing us to take advantage of the large corpus of portrait videos already available on the internet. We demonstrate that our method outperforms previous work in balancing accurate relighting and temporal consistency on a number of real-world portrait videos.

Original languageEnglish (US)
Title of host publicationProceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, WACVW 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages719-728
Number of pages10
ISBN (Electronic)9781665458245
DOIs
StatePublished - 2022
Event2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, WACVW 2022 - Waikoloa, United States
Duration: Jan 4 2022Jan 8 2022

Publication series

NameProceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, WACVW 2022

Conference

Conference2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, WACVW 2022
Country/TerritoryUnited States
CityWaikoloa
Period1/4/221/8/22

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Temporally Consistent Relighting for Portrait Videos'. Together they form a unique fingerprint.

Cite this