Optimal Combination of Image Denoisers

TL;DR

This paper introduces CsNet, a novel framework that optimally combines multiple image denoisers using deep neural networks and convex optimization to enhance denoising performance and detail recovery.

Contribution

It presents a provably optimal combination scheme for denoisers, including a neural network for MSE estimation without ground truth, and an image boosting method.

Findings

CsNet consistently improves denoising results.

The framework effectively combines different denoisers.

Experimental results validate the approach's superiority.

Abstract

Given a set of image denoisers, each having a different denoising capability, is there a provably optimal way of combining these denoisers to produce an overall better result? An answer to this question is fundamental to designing an ensemble of weak estimators for complex scenes. In this paper, we present an optimal combination scheme by leveraging deep neural networks and convex optimization. The proposed framework, called the Consensus Neural Network (CsNet), introduces three new concepts in image denoising: (1) A provably optimal procedure to combine the denoised outputs via convex optimization; (2) A deep neural network to estimate the mean squared error (MSE) of denoised images without needing the ground truths; (3) An image boosting procedure using a deep neural network to improve contrast and to recover lost details of the combined images. Experimental results show that CsNet can consistently improve denoising performance for both deterministic and neural network denoisers.