Mitigating Channel-wise Noise for Single Image Super Resolution
This work addresses a specific issue in image super-resolution for noisy color images, representing an incremental improvement over existing approaches.
The paper tackles the problem of super-resolving noisy color images with channel-wise varying noise, which existing methods ignore, by proposing a method that jointly considers color channels, estimates noise statistics blindly, and uses adaptive weights and regularization terms for low-rank structure and multi-scale details, demonstrating its capability in real scenarios.
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.