ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition

TL;DR

ShadingNet is a deep learning model that decomposes shading into direct and indirect components to improve intrinsic image decomposition, outperforming existing methods on multiple datasets.

Contribution

The paper introduces a novel fine-grained shading decomposition approach with a specialized neural network and provides a large synthetic dataset for training and evaluation.

Findings

Outperforms state-of-the-art algorithms on multiple datasets

Effectively separates direct and indirect shading components

Provides a large-scale synthetic dataset with ground-truths

Abstract

In general, intrinsic image decomposition algorithms interpret shading as one unified component including all photometric effects. As shading transitions are generally smoother than reflectance (albedo) changes, these methods may fail in distinguishing strong photometric effects from reflectance variations. Therefore, in this paper, we propose to decompose the shading component into direct (illumination) and indirect shading (ambient light and shadows) subcomponents. The aim is to distinguish strong photometric effects from reflectance variations. An end-to-end deep convolutional neural network (ShadingNet) is proposed that operates in a fine-to-coarse manner with a specialized fusion and refinement unit exploiting the fine-grained shading model. It is designed to learn specific reflectance cues separated from specific photometric effects to analyze the disentanglement capability. A large-scale dataset of scene-level synthetic images of outdoor natural environments is provided with fine-grained intrinsic image ground-truths. Large scale experiments show that our approach using fine-grained shading decompositions outperforms state-of-the-art algorithms utilizing unified shading on NED, MPI Sintel, GTA V, IIW, MIT Intrinsic Images, 3DRMS and SRD datasets.