Y-Net: Multi-Scale Feature Aggregation Network With Wavelet Structure Similarity Loss Function For Single Image Dehazing

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 stateof-the-art algorithms. Code and models are available at https://github.com/dectrfov/Y-net Index Terms-Single image dehazing, Y-net, discrete wavelet transform, structure similarity, multi-scale feature aggregation

Monocular Depth Estimation with Joint Attention Feature Distillation and Wavelet-Based Loss Function

“…Similar conclusions were found by [ 15 ] and [ 46 ]. Reference [ 46 ] extended the SSIM loss by combining it with DWT and showed that this simple modification could improve reconstruction for single-image dehazing.…”

“…Similar conclusions were found by [ 15 ] and [ 46 ]. Reference [ 46 ] extended the SSIM loss by combining it with DWT and showed that this simple modification could improve reconstruction for single-image dehazing. Reference [ 15 ] showed that simply allocating larger weights to edge areas in the loss function could boost performances in the border areas.…”

“… SSIM loss. Global consistency metric commonly employed for computer vision tasks: where and are the predicted depth map and ground truth means, respectively, and are predicted depth map and ground truth standard deviations, respectively, is the covariance between the predicted depth map and ground truth, and constants = 2 and = 6 follow [ 46 ]. …”

“…Lee et al [ 29 ] proposed a loss rebalancing algorithm to initialize and rebalance weights for loss terms adaptively during training. Yang et al [ 46 ] adopted DWT to reform the structural similarity (SSIM) loss [ 47 ] and achieved improved reconstructions. These methods were proposed to enhance the loss function effectiveness under fixed loss term combinations.…”

Unsupervised monocular depth estimation with aggregating image features and wavelet SSIM (Structural SIMilarity) loss

“…In addition, the accuracy of depth network suffers from some noise (𝑒.𝑔., haze and rain) in the complex images. To reduce the influence of noise, the 2D wavelet discrete transform [21] is applied to SSIM loss, which can recover high-quality clear images. A sample of depth prediction is shown in Figure 1.…”