RGB2AO: Ambient Occlusion Generation from RGB Images. (13th July 2020)

• Record Type: Journal Article
• Authors: Inoue, N.; Ito, D.; Hold‐Geoffroy, Y.; Mai, L.; Price, B.; Yamasaki, T.
• Is Part Of: Computer graphics forum. Volume 39:Number 2(2020)
• Page Start: 451
• Page End: 462
• Publication Date: 2020-07-13
• Subjects: CCS Concepts -- Computing methodologies → Image‐based rendering; Computer graphics -- Periodicals; 006.605
• DOI: 10.1111/cgf.13943
• Languages: English
• ISSNs: 0167-7055

Abstract

Abstract: 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.