Image Denoising via CNNs: An Adversarial Approach

TL;DR

This paper introduces a novel CNN architecture for blind image denoising that combines multi-scale features, regularization, and adversarial training, achieving competitive results.

Contribution

It presents a new CNN design integrating multi-scale features, an l_p regularizer, and adversarial training for improved blind image denoising.

Findings

Achieves competitive denoising performance

Effective noise reduction through multi-scale feature extraction

Enhanced reconstruction with adversarial training

Abstract

Is it possible to recover an image from its noisy version using convolutional neural networks? This is an interesting problem as convolutional layers are generally used as feature detectors for tasks like classification, segmentation and object detection. We present a new CNN architecture for blind image denoising which synergically combines three architecture components, a multi-scale feature extraction layer which helps in reducing the effect of noise on feature maps, an l_p regularizer which helps in selecting only the appropriate feature maps for the task of reconstruction, and finally a three step training approach which leverages adversarial training to give the final performance boost to the model. The proposed model shows competitive denoising performance when compared to the state-of-the-art approaches.