Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images
It addresses a domain-specific problem for remote sensing and image processing by enabling efficient haze removal in ultra-high-resolution images, though it is incremental as it builds on existing deep learning approaches.
The paper tackles haze removal in large, high-resolution images by proposing DehazeXL, which balances global context and local features to enable end-to-end modeling on mainstream GPUs, achieving state-of-the-art results with inference on images up to 10240x10240 pixels using only 21 GB of memory.
Global contextual information and local detail features are essential for haze removal tasks. Deep learning models perform well on small, low-resolution images, but they encounter difficulties with large, high-resolution ones due to GPU memory limitations. As a compromise, they often resort to image slicing or downsampling. The former diminishes global information, while the latter discards high-frequency details. To address these challenges, we propose DehazeXL, a haze removal method that effectively balances global context and local feature extraction, enabling end-to-end modeling of large images on mainstream GPU hardware. Additionally, to evaluate the efficiency of global context utilization in haze removal performance, we design a visual attribution method tailored to the characteristics of haze removal tasks. Finally, recognizing the lack of benchmark datasets for haze removal in large images, we have developed an ultra-high-resolution haze removal dataset (8KDehaze) to support model training and testing. It includes 10000 pairs of clear and hazy remote sensing images, each sized at 8192 $\times$ 8192 pixels. Extensive experiments demonstrate that DehazeXL can infer images up to 10240 $\times$ 10240 pixels with only 21 GB of memory, achieving state-of-the-art results among all evaluated methods. The source code and experimental dataset are available at https://github.com/CastleChen339/DehazeXL.