Sorry, you need to enable JavaScript to visit this website.

Image Restoration with Deep Generative Models

Citation Author(s):
Chen Chen, Alexander G. Schwing, Mark Hasegawa-Johnson, Minh N. Do
Submitted by:
Teck Yian Lim
Last updated:
17 April 2018 - 12:40am
Document Type:
Presentation Slides
Document Year:
2018
Event:
Presenters Name:
Teck Yian Lim
Paper Code:
3208

Abstract 

Abstract: 

Many image restoration problems are ill-posed in nature, hence, beyond the input image, most existing methods rely on a carefully engineered image prior, which enforces some local image consistency in the recovered image. How tightly the prior assumptions are fulfilled has a big impact on the resulting task performance. To obtain more flexibility, in this work, we proposed to design the image prior in a data-driven manner. Instead of explicitly defining the prior, we learn it using deep generative models. We demonstrate that this learned prior can be applied to many image restoration problems using an unified framework.

up
0 users have voted:

Dataset Files

presentation.pdf

(623)