Y-net: Multi-scale feature aggregation network with wavelet structure similarity loss function for single image dehazing

TL;DR

This paper introduces Y-net, a multi-scale feature aggregation network with a novel wavelet-based similarity loss, significantly improving single image dehazing quality through multi-scale feature fusion and wavelet-based loss optimization.

Contribution

The paper presents a new Y-net architecture with a wavelet structure similarity loss function for enhanced image dehazing performance.

Findings

Y-net outperforms state-of-the-art dehazing algorithms.

Wavelet-based loss improves preservation of image details.

Multi-scale feature aggregation enhances dehazing quality.

Abstract

Single image dehazing is the ill-posed two-dimensional signal reconstruction problem. Recently, deep convolutional neural networks (CNN) have been successfully used in many computer vision problems. In this paper, we propose a Y-net that is named for its structure. This network reconstructs clear images by aggregating multi-scale features maps. Additionally, we propose a Wavelet Structure SIMilarity (W-SSIM) loss function in the training step. In the proposed loss function, discrete wavelet transforms are applied repeatedly to divide the image into differently sized patches with different frequencies and scales. The proposed loss function is the accumulation of SSIM loss of various patches with respective ratios. Extensive experimental results demonstrate that the proposed Y-net with the W-SSIM loss function restores high-quality clear images and outperforms state-of-the-art algorithms. Code and models are available at https://github.com/dectrfov/Y-net.