# Image Denoising via CNNs: An Adversarial Approach

Source: [Image Denoising via CNNs: An Adversarial Approach](<https://www.sota2.com/research/paper/68fa638a1e209131ce9ff639>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:44:17.219Z

Authors: Nithish Divakar, R. Venkatesh Babu

Published: 2017-08-01T05:04:22.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1708.00159>)

[PDF](<https://arxiv.org/pdf/1708.00159.pdf>)
