Vision Transformers for Single Image Dehazing

Abstract

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.

References in corpus (1)

• Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer

Cited by in corpus (14)

• A survey of the Vision Transformers and their CNN-Transformer based Variants
• A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends
• Real-World Remote Sensing Image Dehazing: Benchmark and Baseline
• DFR-Net: Density Feature Refinement Network for Image Dehazing Utilizing Haze Density Difference
• HazeSpace2M: A Dataset for Haze Aware Single Image Dehazing
• Advances in Artificial Intelligence: A Review for the Creative Industries
• Towards Context-aware Convolutional Network for Image Restoration
• A General Albedo Recovery Approach for Aerial Photogrammetric Images through Inverse Rendering
• Joint multi-dimensional dynamic attention and transformer for general image restoration
• Remote Sensing Image Dehazing: A Systematic Review of Progress, Challenges, and Prospects
• U-Net-Like Spiking Neural Networks for Single Image Dehazing
• Toward Zero-Shot Learning for Visual Dehazing of Urological Surgical Robots
• VLM-Augmented Degradation Modeling for Image Restoration Under Adverse Weather Conditions
• Enhancing the quality of gauge images captured in smoke and haze scenes through deep learning