ClarifyNet: A high-pass and low-pass filtering based CNN for single image dehazing

Dehazing refers to removing the haze and restoring the details from hazy images. In this paper, we propose ClarifyNet, a novel, end-to-end trainable, convolutional neural network architecture for single image dehazing. We note that a high-pass filter detects sharp edges, texture, and other fine details in the image, whereas a low-pass filter detects color and contrast information. Based on this observation, our key idea is to train ClarifyNet on ground-truth haze-free images, low-pass filtered images, and high-pass filtered images. Based on this observation, we present a shared-encoder multi-decoder model ClarifyNet which employs interconnected parallelization. While training, ground-truth haze-free images, low-pass filtered images, and high-pass filtered images undergo multi-stage filter fusion and attention. By utilizing a weighted loss function composed of SSIM loss and L1 loss, we extract and propagate complementary features. We comprehensively evaluate ClarifyNet on I-HAZE, O-HAZE, Dense-Haze, NH-HAZE, SOTS-Indoor, SOTS-Outdoor, HSTS, and Middlebury datasets. We use PSNR and SSIM metrics and compare the results with previous works. For most datasets, ClarifyNet provides the highest scores. On using EfficientNet-B6 as the backbone, ClarifyNet has 18 M parameters (model size of similar to 71 MB) and a throughput of 8 frames-per-second while processing images of size 2048 x 1024.

Automated summary

In this paper, a novel end-to-end trainable convolutional neural network architecture called ClarifyNet is proposed for single image dehazing. ClarifyNet utilizes low-pass and high-pass filters to extract different types of information and employs a shared-encoder and multi-decoder model structure. By utilizing a weighted loss function, complementary features are extracted and propagated. Experimental results show that ClarifyNet achieves high scores on multiple datasets.