Fast Fourier Intrinsic Network

TL;DR

The paper introduces FFI-Net, a spectral domain neural network for intrinsic image decomposition that converges faster, is lightweight, and achieves state-of-the-art results without auxiliary networks.

Contribution

FFI-Net is a novel spectral domain network that improves intrinsic image decomposition with faster training and no need for auxiliary networks.

Findings

Achieves state-of-the-art performance on multiple datasets.

Operates efficiently in the spectral domain with faster convergence.

Does not require auxiliary networks for training.

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.