# Deep Shading: Convolutional Neural Networks for Screen-Space Shading Oliver Nalbach, Elena Arabadzhiyska, Dushyant Mehta, Hans-Peter Seidel, Tobias Ritschel · 2017 · *Computer Graphics Forum* [file](https://files.dgkn.uk/papers/2017-nalbach-deep-shading-convolutional-neural-networks-for.pdf) · [DOI](https://doi.org/10.1111/cgf.13225) ## Abstract In computer vision, convolutional neural networks (CNNs) have recently achieved new levels of performance for several inverse problems where RGB pixel appearance is mapped to attributes such as positions, normals or reflectance. In computer graphics, screenspace shading has recently increased the visual quality in interactive image synthesis, where per-pixel attributes such as positions, normals or reflectance of a virtual 3D scene are converted into RGB pixel appearance, enabling effects like ambient occlusion, indirect light, scattering, depth-of-field, motion blur, or anti-aliasing. In this paper we consider the diagonal problem: synthesizing appearance from given per-pixel attributes using a CNN. The resulting Deep Shading simulates various screen-space effects at competitive quality and speed while not being programmed by human experts but learned from example images. ## Zotero notes found on 4/10/2026 ## My notes Used CNNs to estimate screen space effects, each effect has different model inputs/outputs. Just using g buffers, no additional interesting input is used. It doesn't handle indirect lighting so well, however AO seems promising (takes 17ms on 768x512 images for inference).