Free-viewpoint Indoor Neural Relighting from Multi-view Stereo

We introduce a neural relighting algorithm for captured indoors scenes, that allows interactive free-viewpoint navigation. Our method allows illumination to be changed synthetically, while coherently rendering cast shadows and complex glossy materials. We start with multiple images of the scene and a three-dimensional mesh obtained by multi-view stereo (MVS) reconstruction. We assume that lighting is well explained as the sum of a view-independent diffuse component and a view-dependent glossy term concentrated around the mirror reflection direction. We design a convolutional network around input feature maps that facilitate learning of an implicit representation of scene materials and illumination, enabling both relighting and free-viewpoint navigation. We generate these input maps by exploiting the best elements of both image-based and physically based rendering. We sample the input views to estimate diffuse scene irradiance, and compute the new illumination caused by user-specified light sources using path tracing. To facilitate the network's understanding of materials and synthesize plausible glossy reflections, we reproject the views and compute mirror images. We train the network on a synthetic dataset where each scene is also reconstructed with MVS. We show results of our algorithm re- lighting real indoor scenes and performing free-viewpoint navigation with complex and realistic glossy reflections, which so far remained out of reach for view-synthesis techniques.

Automated summary

The neural relighting algorithm introduced in this study enables interactive free-viewpoint navigation in captured indoors scenes, allowing synthetic changes in illumination while maintaining coherent rendering of shadows and glossy materials. By utilizing both image-based and physically based rendering elements, along with a three-dimensional mesh obtained through multiview stereo reconstruction, the method facilitates learning of an implicit representation of scene materials and illumination.