We propose DeRenderNet, a deep neural network to decompose the albedo and latent lighting, and render shape-(in)dependent shadings, given a single image of an outdoor urban scene, trained in a self-supervised manner. To achieve this goal, we propose to use the albedo maps extracted from scenes in videogames as direct supervision and pre-compute the normal and shadow prior maps based on the depth maps provided as indirect supervision. Compared with state-of-the-art intrinsic image decomposition methods, DeRenderNet produces shadow-free albedo maps with clean details and an accurate prediction of shadows in the shape-independent shading, which is shown to be effective in re-rendering and improving the accuracy of high-level vision tasks for urban scenes.
@article{arxiv.2104.13602,
title = {DeRenderNet: Intrinsic Image Decomposition of Urban Scenes with Shape-(In)dependent Shading Rendering},
author = {Yongjie Zhu and Jiajun Tang and Si Li and Boxin Shi},
journal= {arXiv preprint arXiv:2104.13602},
year = {2021}
}