Deep Reflectance Maps

TL;DR

This paper introduces a neural network approach for estimating reflectance maps of specular materials under natural lighting, enabling better intrinsic image decomposition and editing applications.

Contribution

It presents a novel end-to-end CNN architecture for reflectance map estimation and a new challenge dataset for specular materials under complex illumination.

Findings

Effective reflectance map predictions on synthetic and real images.

Improved intrinsic image decomposition through indirect supervision.

Application to image editing tasks demonstrates practical utility.

Abstract

Undoing the image formation process and therefore decomposing appearance into its intrinsic properties is a challenging task due to the under-constraint nature of this inverse problem. While significant progress has been made on inferring shape, materials and illumination from images only, progress in an unconstrained setting is still limited. We propose a convolutional neural architecture to estimate reflectance maps of specular materials in natural lighting conditions. We achieve this in an end-to-end learning formulation that directly predicts a reflectance map from the image itself. We show how to improve estimates by facilitating additional supervision in an indirect scheme that first predicts surface orientation and afterwards predicts the reflectance map by a learning-based sparse data interpolation. In order to analyze performance on this difficult task, we propose a new challenge of Specular MAterials on SHapes with complex IllumiNation (SMASHINg) using both synthetic and real images. Furthermore, we show the application of our method to a range of image-based editing tasks on real images.