圖像塊標記化：全局上下文融合實現大尺寸圖像高效去霧

Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images

April 13, 2025

作者: Jiuchen Chen, Xinyu Yan, Qizhi Xu, Kaiqi Li

cs.AI

摘要

全局上下文信息與局部細節特徵對於去霧任務至關重要。深度學習模型在處理小型、低解析度圖像時表現良好，但在面對大型、高解析度圖像時，由於GPU記憶體限制，往往會遇到困難。作為折衷方案，這些模型通常會採用圖像切片或下採樣的方法。前者削弱了全局信息，而後者則丟失了高頻細節。為解決這些挑戰，我們提出了DehazeXL，一種有效平衡全局上下文與局部特徵提取的去霧方法，使得在主流GPU硬體上實現大型圖像的端到端建模成為可能。此外，為了評估全局上下文利用效率對去霧性能的影響，我們設計了一種針對去霧任務特點的視覺歸因方法。最後，考慮到缺乏針對大型圖像去霧的基準數據集，我們開發了一個超高解析度去霧數據集（8KDehaze）以支持模型的訓練與測試。該數據集包含10000對清晰與霧霾的遙感圖像，每張圖像尺寸為8192×8192像素。大量實驗表明，DehazeXL僅需21GB記憶體即可推斷出高達10240×10240像素的圖像，在所有評估方法中取得了最先進的成果。源代碼與實驗數據集可於https://github.com/CastleChen339/DehazeXL獲取。

English

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.