Fast fourier intrinsic network

Yanlin Qian, Miaojing Shi, Joni-Kristian Kämäräinen, Jiri Matas

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

11 Citations (Scopus)
9 Downloads (Pure)

Abstract

We address the problem of decomposing an image into albedo and shading. We propose the Fast Fourier Intrinsic Network, FFI-Net in short, that operates in the spectral domain, splitting the input into several spectral bands. Weights in FFI-Net are optimized in the spectral domain, allowing faster convergence to a lower error. FFI-Net is lightweight and does not need auxiliary networks for training. The network is trained end-to-end with a novel spectral loss which measures the global distance between the network prediction and corresponding ground truth. FFI-Net achieves state-of-the-art performance on MPI-Sintel, MIT Intrinsic, and IIW datasets.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021
PublisherIEEE
Pages3168-3177
Number of pages10
ISBN (Electronic)9780738142661
DOIs
Publication statusPublished - Jan 2021
Publication typeA4 Article in conference proceedings
EventIEEE Winter Conference on Applications of Computer Vision - , United States
Duration: 5 Jan 20219 Jan 2021

Publication series

NameProceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021
ISSN (Electronic)2642-9381

Conference

ConferenceIEEE Winter Conference on Applications of Computer Vision
Country/TerritoryUnited States
Period5/01/219/01/21

Publication forum classification

  • Publication forum level 1

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Fast fourier intrinsic network'. Together they form a unique fingerprint.

Cite this