Generative Adversarial Network based Image Blur Compensation for Projection-Based Mixed Reality
Note: We don't have the ability to review paper
PubDate: February 2020
Teams: Osaka University
Writers: Yuta Kageyama; Mariko Isogawa; Daisuke Iwai; Kosuke Sato
PDF: Generative Adversarial Network based Image Blur Compensation for Projection-Based Mixed Reality
Abstract
Projection-based mixed reality superimposes an image on a real object by a projector. There is a problem that spatially nonuniform blurring occurs in the projected result due to defocus blur and subsurface scattering. As the solution, some methods of applying blur compensation to an input image before projecting have been studied. In this paper, we propose to use a generative adversarial network (GAN) that computes the compensation image from an input image and a projected result.
