Deep intrinsic decomposition trained on surreal scenes yet with realistic light effects

TL;DR

This paper introduces a novel framework for intrinsic image decomposition that uses a flexible image generation process and a physics-informed deep learning architecture, achieving state-of-the-art results on challenging datasets.

Contribution

It presents a new data generation method and a deep learning architecture that incorporates physical constraints for improved intrinsic image decomposition.

Findings

Achieves state-of-the-art performance on intrinsic image datasets.

Provides a versatile and computationally efficient approach.

Addresses dataset limitations with a novel image generation process.

Abstract

Estimation of intrinsic images still remains a challenging task due to weaknesses of ground-truth datasets, which either are too small or present non-realistic issues. On the other hand, end-to-end deep learning architectures start to achieve interesting results that we believe could be improved if important physical hints were not ignored. In this work, we present a twofold framework: (a) a flexible generation of images overcoming some classical dataset problems such as larger size jointly with coherent lighting appearance; and (b) a flexible architecture tying physical properties through intrinsic losses. Our proposal is versatile, presents low computation time, and achieves state-of-the-art results.