Faces as Lighting Probes via Unsupervised Deep Highlight Extraction

TL;DR

This paper introduces an unsupervised deep learning method to estimate detailed scene illumination from human faces in a single image, producing high-precision environment maps by extracting and tracing highlights.

Contribution

It presents a novel unsupervised finetuning scheme for highlight extraction and a deconvolution approach to improve environment map accuracy, outperforming previous methods.

Findings

State-of-the-art accuracy in indoor and outdoor scenes

Effective highlight extraction via deep neural network

Unsupervised finetuning improves real-image performance

Abstract

We present a method for estimating detailed scene illumination using human faces in a single image. In contrast to previous works that estimate lighting in terms of low-order basis functions or distant point lights, our technique estimates illumination at a higher precision in the form of a non-parametric environment map. Based on the observation that faces can exhibit strong highlight reflections from a broad range of lighting directions, we propose a deep neural network for extracting highlights from faces, and then trace these reflections back to the scene to acquire the environment map. Since real training data for highlight extraction is very limited, we introduce an unsupervised scheme for finetuning the network on real images, based on the consistent diffuse chromaticity of a given face seen in multiple real images. In tracing the estimated highlights to the environment, we reduce the blurring effect of skin reflectance on reflected light through a deconvolution determined by prior knowledge on face material properties. Comparisons to previous techniques for highlight extraction and illumination estimation show the state-of-the-art performance of this approach on a variety of indoor and outdoor scenes.