Image Denoising Using Green Channel Prior

TL;DR

This paper introduces a green channel prior-based image denoising method that leverages the higher sampling rate of the green channel and CNN-based noise estimation to improve denoising quality in real-world images.

Contribution

The proposed GCP-ID method integrates green channel prior into patch-based denoising and employs CNNs for adaptive noise estimation, offering a novel approach for real-world image denoising.

Findings

Demonstrates competitive denoising performance on real-world datasets.

Effectively utilizes green channel prior to guide patch grouping.

Employs CNN-based noise estimation for adaptivity.

Abstract

Image denoising is an appealing and challenging task, in that noise statistics of real-world observations may vary with local image contents and different image channels. Specifically, the green channel usually has twice the sampling rate in raw data. To handle noise variances and leverage such channel-wise prior information, we propose a simple and effective green channel prior-based image denoising (GCP-ID) method, which integrates GCP into the classic patch-based denoising framework. Briefly, we exploit the green channel to guide the search for similar patches, which aims to improve the patch grouping quality and encourage sparsity in the transform domain. The grouped image patches are then reformulated into RGGB arrays to explicitly characterize the density of green samples. Furthermore, to enhance the adaptivity of GCP-ID to various image contents, we cast the noise estimation problem into a classification task and train an effective estimator based on convolutional neural networks (CNNs). Experiments on real-world datasets demonstrate the competitive performance of the proposed GCP-ID method for image and video denoising applications in both raw and sRGB spaces. Our code is available at https://github.com/ZhaomingKong/GCP-ID.