PAD-Net: A Perception-Aided Single Image Dehazing Network
This work addresses image quality enhancement for computer vision applications, but it is incremental as it focuses on modifying the loss function in an existing framework.
The paper tackled the problem of single image dehazing by replacing the ℓ2 loss with perceptually derived loss functions in an end-to-end neural network, resulting in a 4.2% relative improvement in PSNR and 2.3% in SSIM on the SOTS set compared to AOD-Net.
In this work, we investigate the possibility of replacing the $\ell_2$ loss with perceptually derived loss functions (SSIM, MS-SSIM, etc.) in training an end-to-end dehazing neural network. Objective experimental results suggest that by merely changing the loss function we can obtain significantly higher PSNR and SSIM scores on the SOTS set in the RESIDE dataset, compared with a state-of-the-art end-to-end dehazing neural network (AOD-Net) that uses the $\ell_2$ loss. The best PSNR we obtained was 23.50 (4.2% relative improvement), and the best SSIM we obtained was 0.8747 (2.3% relative improvement.)