Skip to Main content Skip to Navigation
Journal articles

Free-viewpoint Indoor Neural Relighting from Multi-view Stereo

Abstract : 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 3D 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 relighting 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.
Complete list of metadata
Contributor : Team Reves Connect in order to contact the contributor
Submitted on : Thursday, June 24, 2021 - 8:08:55 PM
Last modification on : Saturday, June 25, 2022 - 11:50:56 PM


Files produced by the author(s)




Julien Philip, Sébastien Morgenthaler, Michaël Gharbi, George Drettakis. Free-viewpoint Indoor Neural Relighting from Multi-view Stereo. ACM Transactions on Graphics, Association for Computing Machinery, 2021, ⟨10.1145/3469842⟩. ⟨hal-03265780v2⟩



Record views


Files downloads