Fast Fourier Intrinsic Network
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.
Cite
Text
Qian et al. "Fast Fourier Intrinsic Network." Winter Conference on Applications of Computer Vision, 2021.Markdown
[Qian et al. "Fast Fourier Intrinsic Network." Winter Conference on Applications of Computer Vision, 2021.](https://mlanthology.org/wacv/2021/qian2021wacv-fast/)BibTeX
@inproceedings{qian2021wacv-fast,
title = {{Fast Fourier Intrinsic Network}},
author = {Qian, Yanlin and Shi, Miaojing and Kamarainen, Joni-Kristian and Matas, Jiri},
booktitle = {Winter Conference on Applications of Computer Vision},
year = {2021},
pages = {3169-3178},
url = {https://mlanthology.org/wacv/2021/qian2021wacv-fast/}
}