Neural Radiance Transfer Fields for Relightable Novel-view Synthesis with Global Illumination

TL;DR

This paper introduces a neural radiance transfer method for relightable novel-view synthesis that models global illumination effects from real images under unknown lighting, improving realism and accuracy.

Contribution

It presents a neural radiance transfer function that implicitly captures global illumination using environment maps, trained with a differentiable path tracer and real images.

Findings

Improved disentanglement of scene parameters.

More realistic and accurate re-rendering results.

Effective scene relighting under novel views and lighting.

Abstract

Given a set of images of a scene, the re-rendering of this scene from novel views and lighting conditions is an important and challenging problem in Computer Vision and Graphics. On the one hand, most existing works in Computer Vision usually impose many assumptions regarding the image formation process, e.g. direct illumination and predefined materials, to make scene parameter estimation tractable. On the other hand, mature Computer Graphics tools allow modeling of complex photo-realistic light transport given all the scene parameters. Combining these approaches, we propose a method for scene relighting under novel views by learning a neural precomputed radiance transfer function, which implicitly handles global illumination effects using novel environment maps. Our method can be solely supervised on a set of real images of the scene under a single unknown lighting condition. To disambiguate the task during training, we tightly integrate a differentiable path tracer in the training process and propose a combination of a synthesized OLAT and a real image loss. Results show that the recovered disentanglement of scene parameters improves significantly over the current state of the art and, thus, also our re-rendering results are more realistic and accurate.