Vision Transformers for Single Image Dehazing

8 Apr 2022  ·  Yuda Song, Zhuqing He, Hui Qian, Xin Du ·

Image dehazing is a representative low-level vision task that estimates latent haze-free images from hazy images. In recent years, convolutional neural network-based methods have dominated image dehazing. However, vision Transformers, which has recently made a breakthrough in high-level vision tasks, has not brought new dimensions to image dehazing. We start with the popular Swin Transformer and find that several of its key designs are unsuitable for image dehazing. To this end, we propose DehazeFormer, which consists of various improvements, such as the modified normalization layer, activation function, and spatial information aggregation scheme. We train multiple variants of DehazeFormer on various datasets to demonstrate its effectiveness. Specifically, on the most frequently used SOTS indoor set, our small model outperforms FFA-Net with only 25% #Param and 5% computational cost. To the best of our knowledge, our large model is the first method with the PSNR over 40 dB on the SOTS indoor set, dramatically outperforming the previous state-of-the-art methods. We also collect a large-scale realistic remote sensing dehazing dataset for evaluating the method's capability to remove highly non-homogeneous haze.

PDF Abstract

Datasets


Introduced in the Paper:

RS-Haze

Used in the Paper:

RESIDE

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Dehazing RESIDE-6K DehazeFormer-B PSNR 31.45 # 1
SSIM 0.98 # 1
Image Dehazing RS-Haze DehazeFormer-B PSNR 39.87 # 1
SSIM 0.971 # 1
Image Dehazing SOTS Indoor DehazeFormer-L PSNR 40.05 # 14
SSIM 0.996 # 6
Image Dehazing SOTS Outdoor DehazeFormer-B PSNR 34.95 # 15
SSIM 0.984 # 15

Methods