MixDehazeNet : Mix Structure Block For Image Dehazing Network

28 May 2023  ·  LiPing Lu, Qian Xiong, DuanFeng Chu, Bingrong Xu ·

Image dehazing is a typical task in the low-level vision field. Previous studies verified the effectiveness of the large convolutional kernel and attention mechanism in dehazing. However, there are two drawbacks: the multi-scale properties of an image are readily ignored when a large convolutional kernel is introduced, and the standard series connection of an attention module does not sufficiently consider an uneven hazy distribution. In this paper, we propose a novel framework named Mix Structure Image Dehazing Network (MixDehazeNet), which solves two issues mentioned above. Specifically, it mainly consists of two parts: the multi-scale parallel large convolution kernel module and the enhanced parallel attention module. Compared with a single large kernel, parallel large kernels with multi-scale are more capable of taking partial texture into account during the dehazing phase. In addition, an enhanced parallel attention module is developed, in which parallel connections of attention perform better at dehazing uneven hazy distribution. Extensive experiments on three benchmarks demonstrate the effectiveness of our proposed methods. For example, compared with the previous state-of-the-art methods, MixDehazeNet achieves a significant improvement (42.62dB PSNR) on the SOTS indoor dataset. The code is released in https://github.com/AmeryXiong/MixDehazeNet.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Dehazing Haze4k MixDehazeNet PSNR 35.64 # 1
SSIM 0.992 # 1
Image Dehazing RESIDE-6K MixDehazeNet PSNR 30.18 # 2
SSIM 0.973 # 2
Image Dehazing SOTS Indoor MixDehazeNet PSNR 42.62 # 2
SSIM 0.997 # 1
Image Dehazing SOTS Outdoor MixDehazeNet PSNR 36.50 # 14
SSIM 0.986 # 13

Methods