# Fast Fourier Intrinsic Network

arXiv: https://arxiv.org/abs/2011.04612 · HTML: https://mlsanity.com/paper/2011.04612/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2020.

## Built on by (most cited first, 1 of 1)

- [Intrinsic Image Decomposition Using Point Cloud Representation](https://mlsanity.com/paper/2307.10924/) (2023)

## Abstract (arXiv)

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.