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

by   Yu-Ying Yeh, et al.

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.


page 1

page 5

page 12

page 14

page 16

page 17

page 20

page 21


Portrait Shadow Manipulation

Casually-taken portrait photographs often suffer from unflattering light...

A New Dimension in Testimony: Relighting Video with Reflectance Field Exemplars

We present a learning-based method for estimating 4D reflectance field o...

Relighting Humans in the Wild: Monocular Full-Body Human Relighting with Domain Adaptation

The modern supervised approaches for human image relighting rely on trai...

Learning Neural Transmittance for Efficient Rendering of Reflectance Fields

Recently neural volumetric representations such as neural reflectance fi...

Neural Re-Simulation for Generating Bounces in Single Images

We introduce a method to generate videos of dynamic virtual objects plau...

Relighting4D: Neural Relightable Human from Videos

Human relighting is a highly desirable yet challenging task. Existing wo...

Spatially-Varying Outdoor Lighting Estimation from Intrinsics

We present SOLID-Net, a neural network for spatially-varying outdoor lig...