NeLF: Neural Light-transport Field for Portrait View Synthesis and Relighting

TL;DR

NeLF introduces a neural network-based system for synthesizing novel portrait views and relighting under new lighting conditions, generalizing well from synthetic training data to real portraits with high accuracy.

Contribution

The paper presents a novel neural light-transport field model for combined portrait view synthesis and relighting, outperforming previous methods.

Findings

Achieves state-of-the-art results in portrait view synthesis and relighting.

Generalizes effectively from synthetic training data to real portraits.

Handles multiple lighting conditions and viewpoints simultaneously.

Abstract

Human portraits exhibit various appearances when observed from different views under different lighting conditions. We can easily imagine how the face will look like in another setup, but computer algorithms still fail on this problem given limited observations. To this end, we present a system for portrait view synthesis and relighting: given multiple portraits, we use a neural network to predict the light-transport field in 3D space, and from the predicted Neural Light-transport Field (NeLF) produce a portrait from a new camera view under a new environmental lighting. Our system is trained on a large number of synthetic models, and can generalize to different synthetic and real portraits under various lighting conditions. Our method achieves simultaneous view synthesis and relighting given multi-view portraits as the input, and achieves state-of-the-art results.