Fast Fourier Intrinsic Network
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00354246" target="_blank" >RIV/68407700:21230/21:00354246 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1109/WACV48630.2021.00321" target="_blank" >https://doi.org/10.1109/WACV48630.2021.00321</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/WACV48630.2021.00321" target="_blank" >10.1109/WACV48630.2021.00321</a>
Alternative languages
Result language
angličtina
Original language name
Fast Fourier Intrinsic Network
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Research Center for Informatics</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021
ISBN
978-0-7381-4266-1
ISSN
2472-6737
e-ISSN
2642-9381
Number of pages
10
Pages from-to
3168-3177
Publisher name
IEEE Computer Society
Place of publication
USA
Event location
Waikoloa, HI
Event date
Jan 5, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000693397600117