PAD-Net: A Perception-Aided Single Image Dehazing Network
share
In this work, we investigate the possibility of replacing the ℓ_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 ℓ_2 loss. The best PSNR we obtained was 23.50 (4.2 and the best SSIM we obtained was 0.8747 (2.3
READ FULL TEXT