# Dual-Path Adversarial Denoising Network Based on UNet

## TL;DR

This paper introduces a new image denoising method using a dual-path adversarial network to better preserve details while removing noise.

## Contribution

A novel three-module architecture with a dual-path UNet denoiser and adversarial training for improved image denoising.

## Key findings

- The method outperforms state-of-the-art GAN variants on SIDD, DND, and PolyU datasets.
- It effectively preserves fine details and global structures in complex noise scenarios.
- The dual-path design enhances adaptability to various noise types while maintaining image fidelity.

## Abstract

Digital image quality is crucial for reliable analysis in applications such as medical imaging, satellite remote sensing, and video surveillance. However, traditional denoising methods struggle to balance noise removal with detail preservation and lack adaptability to various types of noise. We propose a novel three-module architecture for image denoising, comprising a generator, a dual-path-UNet-based denoiser, and a discriminator. The generator creates synthetic noise patterns to augment training data, while the dual-path-UNet denoiser uses multiple receptive field modules to preserve fine details and dense feature fusion to maintain global structural integrity. The discriminator provides adversarial feedback to enhance denoising performance. This dual-path adversarial training mechanism addresses the limitations of traditional methods by simultaneously capturing both local details and global structures. Experiments on the SIDD, DND, and PolyU datasets demonstrate superior performance. We compare our architecture with the latest state-of-the-art GAN variants through comprehensive qualitative and quantitative evaluations. These results confirm the effectiveness of noise removal with minimal loss of critical image details. The proposed architecture enhances image denoising capabilities in complex noise scenarios, providing a robust solution for applications that require high image fidelity. By enhancing adaptability to various types of noise while maintaining structural integrity, this method provides a versatile tool for image processing tasks that require preserving detail.