Martin, RosalieMeyer, ArthurPesare, DavideBoubekeur, Tamy and Sen, Pradeep2019-07-142019-07-142019978-3-03868-095-61727-3463https://doi.org/10.2312/sr.20191222https://diglib.eg.org:443/handle/10.2312/sr20191222We propose a deep-learning based method for the removal of shades, projected shadows and highlights from a single picture of a quasi-planar surface captured in natural lighting conditions with any kind of camera device. To achieve this, we train an encoder-decoder to process physically based materials, rendered under various lighting conditions, to infer its spatially-varying albedo. Our network processes relatively small image tiles (512x512 pixels) and we propose a solution to handle larger image resolutions by solving a Poisson system across these tiles.10.2312/sr.2019122269-72