Fast fourier intrinsic network

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

Tutkimustuotos: KonferenssiartikkeliScientificvertaisarvioitu

Abstrakti

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.

AlkuperäiskieliEnglanti
OtsikkoProceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021
KustantajaIEEE
Sivut3168-3177
Sivumäärä10
ISBN (elektroninen)9780738142661
DOI - pysyväislinkit
TilaJulkaistu - tammik. 2021
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE Winter Conference on Applications of Computer Vision - , Yhdysvallat
Kesto: 5 tammik. 20219 tammik. 2021

Julkaisusarja

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

Conference

ConferenceIEEE Winter Conference on Applications of Computer Vision
Maa/AlueYhdysvallat
Ajanjakso5/01/219/01/21

Julkaisufoorumi-taso

  • Jufo-taso 1

!!ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Siteeraa tätä