RGB2AO: Ambient Occlusion Generation from RGB Images

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...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Computer graphics forum Ročník 39; číslo 2; s. 451 - 462
Hlavní autoři:	Inoue, N., Ito, D., Hold‐Geoffroy, Y., Mai, L., Price, B., Yamasaki, T.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Oxford Blackwell Publishing Ltd 01.05.2020
Témata:	Artificial neural networks CCS Concepts Color imagery Computing methodologies → Image‐based rendering Image contrast Image enhancement Image filters Occlusion Shading
ISSN:	0167-7055, 1467-8659
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	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.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ISSN:	0167-7055 1467-8659
DOI:	10.1111/cgf.13943