Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation

TL;DR

This paper introduces a novel portrait relighting method that uses a virtual light stage and synthetic-to-real adaptation, eliminating the need for expensive data collection rigs while achieving state-of-the-art photorealistic results.

Contribution

It proposes a new approach combining physically-based synthetic data generation with a synthetic-to-real adaptation for high-quality portrait relighting without a light stage.

Findings

Achieves state-of-the-art relighting quality.

Provides controllable glares and temporal consistency.

Eliminates need for expensive light stage data.

Abstract

Given a portrait image of a person and an environment map of the target lighting, portrait relighting aims to re-illuminate the person in the image as if the person appeared in an environment with the target lighting. To achieve high-quality results, recent methods rely on deep learning. An effective approach is to supervise the training of deep neural networks with a high-fidelity dataset of desired input-output pairs, captured with a light stage. However, acquiring such data requires an expensive special capture rig and time-consuming efforts, limiting access to only a few resourceful laboratories. To address the limitation, we propose a new approach that can perform on par with the state-of-the-art (SOTA) relighting methods without requiring a light stage. Our approach is based on the realization that a successful relighting of a portrait image depends on two conditions. First, the method needs to mimic the behaviors of physically-based relighting. Second, the output has to be photorealistic. To meet the first condition, we propose to train the relighting network with training data generated by a virtual light stage that performs physically-based rendering on various 3D synthetic humans under different environment maps. To meet the second condition, we develop a novel synthetic-to-real approach to bring photorealism to the relighting network output. In addition to achieving SOTA results, our approach offers several advantages over the prior methods, including controllable glares on glasses and more temporally-consistent results for relighting videos.