Premium
RGB2AO: Ambient Occlusion Generation from RGB Images
Author(s) -
Inoue N.,
Ito D.,
HoldGeoffroy Y.,
Mai L.,
Price B.,
Yamasaki T.
Publication year - 2020
Publication title -
computer graphics forum
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.578
H-Index - 120
eISSN - 1467-8659
pISSN - 0167-7055
DOI - 10.1111/cgf.13943
Subject(s) - rgb color model , artificial intelligence , computer science , computer vision , convolutional neural network , image (mathematics) , contrast (vision) , task (project management) , filter (signal processing) , management , economics
We 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 geometry‐aware 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.