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

When Spatially-Variant Filtering Meets Low-Rank Regularization: Exploiting Non-Local Similarity for Single Image Interpolation

Citation Author(s):
Submitted by:
Lantao Yu
Last updated:
25 September 2019 - 11:39am
Document Type:
Presentation Slides
Document Year:
2019
Event:
Presenters:
Lantao Yu
Paper Code:
3833

Abstract

This paper combines spatially-variant filtering and non-local low-rank regularization (NLR) to exploit non-local similarity in natural images in addressing the problem of image interpolation. We propose to build a carefully designed spatially-variant, non-local filtering scheme to generate a reliable estimate of the interpolated image and utilize NLR to refine the estimation. Our work uses a simple, parallelizable algorithm without the need to solve complicated optimization problems. Experiment results demonstrate that our algorithm significantly improves PSNR and SSIM of the interpolated images compared with state-of-the-art algorithms.

up
0 users have voted:

Files

When spatially-variant filtering meets low rank approximation.pdf

(240)