Fast and Flexible Image Blind Denoising via Competition of Experts

TL;DR

This paper presents an efficient ensemble network for image blind denoising that automatically clusters noisy data, significantly reducing computational costs while maintaining high denoising performance.

Contribution

The proposed method introduces a scalable ensemble architecture trained via expert competition, enabling effective denoising across diverse noise types with minimal computational overhead.

Findings

Reduces computational cost by up to 90% compared to single models.

Outperforms existing algorithms in efficiency and denoising quality.

Automatically clusters noisy datasets for optimized denoising performance.

Abstract

Fast and flexible processing are two essential requirements for a number of practical applications of image denoising. Current state-of-the-art methods, however, still require either high computational cost or limited scopes of the target. We introduce an efficient ensemble network trained via a competition of expert networks, as an application for image blind denoising. We realize automatic division of unlabeled noisy datasets into clusters respectively optimized to enhance denoising performance. The architecture is scalable, can be extended to deal with diverse noise sources/levels without increasing the computation time. Taking advantage of this method, we save up to approximately 90% of computational cost without sacrifice of the denoising performance compared to single network models with identical architectures. We also compare the proposed method with several existing algorithms and observe significant outperformance over prior arts in terms of computational efficiency.