Inoue, NaotoIto, DaichiHold-Geoffroy, YannickMai, LongPrice, BrianYamasaki, ToshihikoPanozzo, Daniele and Assarsson, Ulf2020-05-242020-05-2420201467-8659https://doi.org/10.1111/cgf.13943https://diglib.eg.org:443/handle/10.1111/cgf13943We present RGB2AO, a novel task to generate ambient occlusion (AO) from a single RGB image instead of screen space buffers such as depth and normal. RGB2AO produces a new image filter that creates a non-directional shading effect that darkens enclosed and sheltered areas. RGB2AO aims to enhance two 2D image editing applications: image composition and geometryaware contrast enhancement. We first collect a synthetic dataset consisting of pairs of RGB images and AO maps. Subsequently, we propose a model for RGB2AO by supervised learning of a convolutional neural network (CNN), considering 3D geometry of the input image. Experimental results quantitatively and qualitatively demonstrate the effectiveness of our model.Attribution 4.0 International LicenseComputing methodologiesImagebased rendering10.1111/cgf.13943451-462