CNN based Learning using Reflection and Retinex Models for Intrinsic Image Decomposition

TL;DR

This paper introduces a hybrid deep learning approach for intrinsic image decomposition that integrates traditional physics-based reflection models with gradient-based learning, resulting in improved qualitative and quantitative results.

Contribution

It combines deep learning with traditional reflection models and gradient information to enhance intrinsic image decomposition performance.

Findings

Outperforms existing methods in quantitative benchmarks.

Produces sharper edges and better color reproduction.

Fast computation and comprehensive intrinsic component integration.

Abstract

Most of the traditional work on intrinsic image decomposition rely on deriving priors about scene characteristics. On the other hand, recent research use deep learning models as in-and-out black box and do not consider the well-established, traditional image formation process as the basis of their intrinsic learning process. As a consequence, although current deep learning approaches show superior performance when considering quantitative benchmark results, traditional approaches are still dominant in achieving high qualitative results. In this paper, the aim is to exploit the best of the two worlds. A method is proposed that (1) is empowered by deep learning capabilities, (2) considers a physics-based reflection model to steer the learning process, and (3) exploits the traditional approach to obtain intrinsic images by exploiting reflectance and shading gradient information. The proposed model is fast to compute and allows for the integration of all intrinsic components. To train the new model, an object centered large-scale datasets with intrinsic ground-truth images are created. The evaluation results demonstrate that the new model outperforms existing methods. Visual inspection shows that the image formation loss function augments color reproduction and the use of gradient information produces sharper edges. Datasets, models and higher resolution images are available at https://ivi.fnwi.uva.nl/cv/retinet.