Paper Info
Title
Natural And Realistic Single Image Super-Resolution With Explicit Natural Manifold Discrimination
Abstract
Recently, many convolutional neural networksfor single image super-resolution (SISR) have been proposed, which focus on reconstructingthe high-resolutionimages in terms of objective distortion measures. However, the networks trainedwith objective lossfunctions generallyfail to reconstructthe realisticfine textures and details that are essential for better perceptual quality. Recovering the realistic details remains a challengingproblem, and only a few works have been proposed which aim at increasing the perceptual quality by generating enhanced textures. However the generatedfake details often make undesirableartifacts and the overall image looks somewhat unnatural. Therefore, in thispaper,we present a new approachto reconstructingrealistic super-resolved images with high perceptualquality, while maintainingthe naturalnessof the result. In particular we focus on the domain priorpropertiesof SISR problem. Specifically, we define the naturalnesspriorin the lowlevel domain and constrain the output image in the natural manifold, which eventually generates more natural and realistic images. Our results show better naturalness compared to the recent super-resolution algorithms including perception-orientedones.
Year
DOI
Venue
2019
10.1109/CVPR.2019.00831
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
Field
DocType
ISSN
Computer vision,Computer science,Artificial intelligence,Superresolution,Manifold
Conference
1063-6919
Citations 
PageRank 
References 
8
0.44
0
Authors
4
Name
Order
Citations
PageRank
Jae Woong Soh1266.76
Gu Yong Park2110.81
Junho Jo381.79
Nam Ik Cho4712106.98