不良氣候圖像修復旨在移除因惡劣天氣情況 (如霧霾、雨水和 積雪) 而導致的偽影。現存的方法在處理單一氣候圖像修復領域中 取得了卓越的成果，但在面對現實世界常發生的不可預測氣候時， 卻面臨挑戰。雖然不同類別的氣候條件展現出不同的退化模式， 但彼此之間仍舊存在一些高度有關或互補的共同特徵，例如因退 化模式造成的遮掩、因大氣粒子散射引起的顏色失真和對比度衰 減。因此，我們專注利用多種天氣類別下的共同知識，藉由多合 一的方法以進行圖像修復。
於本篇文章中，我們提出三重注意力網路 (TANet)，採用高效 能的方式解決多合一的不良氣候影像修復問題。TANet 包含三重 注意力模塊 (TAB)，該模塊整合了三種類型的注意力機制:使用 局部像素級注意力 (LPA) 和全局條帶級注意力 (GSA) 以解決非均 勻退化模式引起的遮擋問題，使用全局分佈注意力 (GDA) 以解決 由大氣現象引起的顏色失真及對比度衰減。透過利用不同天氣場 景下的共享知識，TANet 成功地以一體化的方式處理多樣不良氣 候。實驗結果表明，TANet 得以高效能且有效率地處理多合一的 不良氣候圖像修復，並達到最先進的性能。

Adverse weather image restoration aims to remove unwanted de- graded artifacts, including haze, rain, and snow, caused by adverse weather conditions. Existing methods achieve remarkable results for addressing single-weather conditions. However, they face challenges when encoun- tering unpredictable weather conditions, which often happens in real- world scenarios. Although different types of weather conditions exhibit different degraded patterns, they share common characteristics that are highly related and complementary, such as occlusions caused by de- graded patterns, color distortion and contrast attenuation owing to the scattering of atmospheric particles. Therefore, we focus on leveraging common knowledge across multiple weather conditions to restore im- ages in a unified manner.
In this paper, we propose a Triplet Attention Network (TANet) to effi- ciently and effectively address all-in-one adverse weather image restora- tion. TANet consists of Triplet Attention Block (TAB) that incorporates three types of attention mechanisms: Local Pixel-wise Attention (LPA) and Global Strip-wise Attention (GSA) to address occlusions caused by non-uniform degraded patterns, and Global Distribution Attention (GDA) to address color distortion and contrast attenuation caused by atmospheric phenomena. By leveraging common knowledge shared across different weather conditions, TANet successfully addresses multiple weather con- ditions in a unified manner. Extensive experimental results show that TANet efficiently and effectively attains state-of-the-art performance in all-in-one adverse weather image restoration.

[1] B. Li, W. Ren, D. Fu, D. Tao, D. Feng, W. Zeng, and Z. Wang, “Benchmarking single- image dehazing and beyond,” IEEE TIP, 2019.
[2] X. Fu, J. Huang, D. Zeng, Y. Huang, X. Ding, and J. Paisley, “Removing rain from single images via a deep detail network,” in CVPR, 2017.
[3] Y.-F. Liu, D.-W. Jaw, S.-C. Huang, and J.-N. Hwang, “Desnownet: Context-aware deep network for snow removal,” IEEE TIP, 2018.
[4] H. Zhang, Y. Ba, E. Yang, V. Mehra, B. Gella, A. Suzuki, A. Pfahnl, C. C. Chandrappa, A. Wong, and A. Kadambi, “Weatherstream: Light transport automation of single image deweathering,” in CVPR, 2023.
[5] H. Wu, Y. Qu, S. Lin, J. Zhou, R. Qiao, Z. Zhang, Y. Xie, and L. Ma, “Contrastive learning for compact single image dehazing,” in CVPR, 2021.
[6] Z. Zheng, W. Ren, X. Cao, X. Hu, T. Wang, F. Song, and X. Jia, “Ultra-high-definition image dehazing via multi-guided bilateral learning,” in CVPR, 2021.
[7] C.-L. Guo, Q. Yan, S. Anwar, R. Cong, W. Ren, and C. Li, “Image dehazing transformer with transmission-aware 3d position embedding,” in CVPR, 2022.
[8] Y. Song, Z. He, H. Qian, and X. Du, “Vision transformers for single image dehazing,” IEEE TIP, 2023.
[9] X. Liu, Y. Ma, Z. Shi, and J. Chen, “Griddehazenet: Attention-based multi-scale network for image dehazing,” in ICCV, 2019.
[10] Q. Deng, Z. Huang, C.-C. Tsai, and C.-W. Lin, “Hardgan: A haze-aware representation distillation gan for single image dehazing,” in ECCV, 2020.
[11] H. Yu, N. Zheng, M. Zhou, J. Huang, Z. Xiao, and F. Zhao, “Frequency and spatial dual guidance for image dehazing,” in ECCV, 2022.
[12] X. Qin, Z. Wang, Y. Bai, X. Xie, and H. Jia, “Ffa-net: Feature fusion attention network for single image dehazing,” in AAAI, 2020.
[13] C. Chen and H. Li, “Robust representation learning with feedback for single image derain- ing,” in CVPR, 2021.
[14] X. Hu, C.-W. Fu, L. Zhu, and P.-A. Heng, “Depth-attentional features for single-image rain removal,” in CVPR, 2019.
[15] H. Wang, Q. Xie, Q. Zhao, and D. Meng, “A model-driven deep neural network for single image rain removal,” in CVPR, 2020.
[16] T. Wang, X. Yang, K. Xu, S. Chen, Q. Zhang, and R. W. Lau, “Spatial attentive single- image deraining with a high quality real rain dataset,” in CVPR, 2019.
[17] R. Li, L.-F. Cheong, and R. T. Tan, “Heavy rain image restoration: Integrating physics model and conditional adversarial learning,” in CVPR, 2019.
[18] W.-T. Chen, H.-Y. Fang, J.-J. Ding, C.-C. Tsai, and S.-Y. Kuo, “Jstasr: Joint size and transparency-aware snow removal algorithm based on modified partial convolution and veiling effect removal,” in ECCV, 2020.
[19] W.-T. Chen, H.-Y. Fang, C.-L. Hsieh, C.-C. Tsai, I. Chen, J.-J. Ding, S.-Y. Kuo, et al., “All snow removed: Single image desnowing algorithm using hierarchical dual-tree complex wavelet representation and contradict channel loss,” in ICCV, 2021.
[20] K. Zhang, R. Li, Y. Yu, W. Luo, and C. Li, “Deep dense multi-scale network for snow removal using semantic and geometric priors,” IEEE TIP, 2021.
[21] Y.Wang,S.Liu,C.Chen,andB.Zeng,“Ahierarchicalapproachforrainorsnowremoving in a single color image,” IEEE TIP, 2017.
[22] S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan, and M.-H. Yang, “Restormer: Efficient transformer for high-resolution image restoration,” in CVPR, 2022.
[23] S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan, M.-H. Yang, and L. Shao, “Multi- stage progressive image restoration,” in CVPR, 2021.
[24] Y. Cui, W. Ren, X. Cao, and A. Knoll, “Focal network for image restoration,” in CVPR, 2023.
[25] Z. Wang, X. Cun, J. Bao, W. Zhou, J. Liu, and H. Li, “Uformer: A general u-shaped transformer for image restoration,” in CVPR, 2022.
[26] L.Chen,X.Chu,X.Zhang,andJ.Sun,“Simplebaselinesforimagerestoration,”inECCV, 2022.
[27] Z.ZhangandM.Hoai,“Objectdetectionwithself-supervisedsceneadaptation,”inCVPR, 2023.
[28] J. Li, R. Xu, J. Ma, Q. Zou, J. Ma, and H. Yu, “Domain adaptive object detection for autonomous driving under foggy weather,” in WACV, 2023.
[29] V. Sindagi, P. Oza, R. Yasarla, and V. Patel, “Prior-based domain adaptive object detection for hazy and rainy conditions,” in ECCV, 2020.
[30] W. Liu, G. Ren, R. Yu, S. Guo, J. Zhu, and L. Zhang, “Image-adaptive yolo for object detection in adverse weather conditions,” in AAAI, 2022.
[31] A. Kerim, F. Chamone, W. L. Ramos, L. S. Marcolino, E. R. Nascimento, and R. Jiang, “Semantic segmentation under adverse conditions: A weather and nighttime-aware syn- thetic data-based approach,” in BMVC, 2022.
[32] T. Kalb and J. Beyerer, “Principles of forgetting in domain-incremental semantic segmen- tation in adverse weather conditions,” in CVPR, 2023.
[33] S. Lee, T. Son, and S. Kwak, “Fifo: Learning fog-invariant features for foggy scene seg- mentation,” in CVPR, 2022.
[34] M. Botet Colomer, P. L. Dovesi, T. Panagiotakopoulos, J. F. Carvalho, L. Härenstam- Nielsen, H. Azizpour, H. Kjellström, D. Cremers, and M. Poggi, “To adapt or not to adapt? real-time adaptation for semantic segmentation,” in ICCV, 2023.
[35] B. Li, X. Liu, P. Hu, Z. Wu, J. Lv, and X. Peng, “All-In-One Image Restoration for Un- known Corruption,” in CVPR, 2022.
[36] W.-T. Chen, Z.-K. Huang, C.-C. Tsai, H.-H. Yang, J.-J. Ding, and S.-Y. Kuo, “Learning multiple adverse weather removal via two-stage knowledge learning and multi-contrastive regularization: Toward a unified model,” in CVPR, 2022.
[37] D. Park, B. H. Lee, and S. Y. Chun, “All-in-one image restoration for unknown degrada- tions using adaptive discriminative filters for specific degradations,” in CVPR, 2023.
[38] P. W. Patil, S. Gupta, S. Rana, S. Venkatesh, and S. Murala, “Multi-weather image restora- tion via domain translation,” in ICCV, 2023.
[39] V. Potlapalli, S. W. Zamir, S. Khan, and F. Khan, “Promptir: Prompting for all-in-one image restoration,” in NeurIPS, 2023.
[40] J. M. J. Valanarasu, R. Yasarla, and V. M. Patel, “Transweather: Transformer-based restoration of images degraded by adverse weather conditions,” in CVPR, 2022.
[41] X. Huang and S. Belongie, “Arbitrary style transfer in real-time with adaptive instance normalization,” in ICCV, 2017.
[42] Y. Liu, J. He, J. Gu, X. Kong, Y. Qiao, and C. Dong, “Degae: A new pretraining paradigm for low-level vision,” in CVPR, 2023.
[43] Y. Qiu, K. Zhang, C. Wang, W. Luo, H. Li, and Z. Jin, “Mb-taylorformer: Multi-branch efficient transformer expanded by taylor formula for image dehazing,” in ICCV, 2023.
[44] X. Li, J. Wu, Z. Lin, H. Liu, and H. Zha, “Recurrent squeeze-and-excitation context ag- gregation net for single image deraining,” in ECCV, 2018.
[45] K. Jiang, Z. Wang, P. Yi, C. Chen, B. Huang, Y. Luo, J. Ma, and J. Jiang, “Multi-scale progressive fusion network for single image deraining,” in CVPR, 2020.
[46] D. Ren, W. Shang, P. Zhu, Q. Hu, D. Meng, and W. Zuo, “Single image deraining using bilateral recurrent network,” IEEE TIP, 2020.
[47] X. Chen, H. Li, M. Li, and J. Pan, “Learning a sparse transformer network for effective image deraining,” in CVPR, 2023.
[48] J. Xiao, X. Fu, A. Liu, F. Wu, and Z.-J. Zha, “Image de-raining transformer,” IEEE TPAMI, 2022.
[49] H. Zhao, Y. Gou, B. Li, D. Peng, J. Lv, and X. Peng, “Comprehensive and delicate: An efficient transformer for image restoration,” in CVPR, June 2023.
[50] Y. Li, Y. Fan, X. Xiang, D. Demandolx, R. Ranjan, R. Timofte, and L. Van Gool, “Efficient and explicit modelling of image hierarchies for image restoration,” in CVPR, 2023.
[51] W.-S. Lai, J.-B. Huang, N. Ahuja, and M.-H. Yang, “Deep laplacian pyramid networks for fast and accurate super-resolution,” in CVPR, 2017.
[52] L. Chen, X. Lu, J. Zhang, X. Chu, and C. Chen, “Hinet: Half instance normalization network for image restoration,” in CVPRW, 2021.
[53] H. Mu, H. Le, B. Yikai, R. Jian, X. Jin, and Y. Jian, “Ra-depth: Resolution adaptive self- supervised monocular depth estimation,” in ECCV, 2022.
[54] W. Wang, F. Chang, T. Ji, and X. Wu, “A fast single-image dehazing method based on a physical model and gray projection,” IEEE Access, 2018.
[55] Q. Hou, L. Zhang, M.-M. Cheng, and J. Feng, “Strip Pooling: Rethinking spatial pooling for scene parsing,” in CVPR, 2020.
[56] S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, “Cbam: Convolutional block attention mod- ule,” in ECCV (V. Ferrari, M. Hebert, C. Sminchisescu, and Y. Weiss, eds.), 2018.
[57] Y. Zhu, T. Wang, X. Fu, X. Yang, X. Guo, J. Dai, Y. Qiao, and X. Hu, “Learning weather- general and weather-specific features for image restoration under multiple adverse weather conditions,” in CVPR, 2023.
[58] Y. Li, Y. Fan, X. Xiang, D. Demandolx, R. Ranjan, R. Timofte, and L. V. Gool, “Efficient and explicit modelling of image hierarchies for image restoration,” in CVPR, 2023.