Mitigating Channel-wise Noise for Single Image Super Resolution

TL;DR

This paper introduces a novel super-resolution method that jointly considers color channels and their noise characteristics, using adaptive weighting, nuclear norm regularization, and multi-scale PCA-based regularization to improve image quality.

Contribution

It proposes a new approach that estimates noise per channel and incorporates low-rank and multi-scale regularizations for enhanced super-resolution performance.

Findings

Effective noise estimation per channel

Improved super-resolution results in real scenarios

Utilizes low-rank and multi-scale regularizations

Abstract

In practice, images can contain different amounts of noise for different color channels, which is not acknowledged by existing super-resolution approaches. In this paper, we propose to super-resolve noisy color images by considering the color channels jointly. Noise statistics are blindly estimated from the input low-resolution image and are used to assign different weights to different color channels in the data cost. Implicit low-rank structure of visual data is enforced via nuclear norm minimization in association with adaptive weights, which is added as a regularization term to the cost. Additionally, multi-scale details of the image are added to the model through another regularization term that involves projection onto PCA basis, which is constructed using similar patches extracted across different scales of the input image. The results demonstrate the super-resolving capability of the approach in real scenarios.