Abstract
In computer vision, transformers have shown increasing effectiveness for high-level vision tasks. To further cope with low-level vision tasks, we propose a general framework, namely local reasoning back-projection transformer (LRB-T) for removing multiple types of bad weather (rain, haze, rain fog, raindrop, et al.) affecting images. Specifically, this paper first integrates the back-projection mechanism into the transformer architecture, where iterative up- and down-projection modules effectively feed and correct the feature reconstruction errors for spatial information preservation, and reduce computational costs since nearly half of the feature maps participate in the back-projection using half resolution. Besides, the proposed adaptive local reasoning block captures important neighborhood information through multiple local reasoning schemes. It can aggregate adjacent tokens to produce spatial-specific involution kernels, attention weights and dynamic positional encodings for local structure updating, and provide implicit spatial feature transform to achieve spatial-wise feature modulation. A pyramid scale guidance module is also established to enable arbitrary size generation consistent with the input, and generate scale-dependent trainable parameters to enhance skip connections. Extensive experiments on four types of well-known bad weather datasets show that the proposed LRB-T improves the image deraining, dehazing, de-rain fog and de-raindrop performance in terms of PSNR and SSIM effectively and outperforms state-of-the-art task-specific bad weather removal methods.
Similar content being viewed by others
Data availability
It is confirmed by the authors that data supporting this research finding are present within the paper, and the publicly available datasets used in this study are rain datasets Rain100L [19], Rain100H [19], DDN-data [17], DID-data [18] and RealRain-data [50], haze datasets SOTS [51], HazeRD [52], NTIRE2018 [53] and URHI [51], rain fog dataset rain fog-data [35] and raindrop dataset RainDrop-data [24].
References
Fu X, Qi Q, Zha Z-J, Zhu Y, Ding X (2021) Rain streak removal via dual graph convolutional network. In: Proceedings of the AAAI conference on artificial intelligence (AAAI), vol 35, pp 1352–1360
Jiang K, Wang Z, Yi P, Chen C, Huang B, Luo Y, Ma J, Jiang J (2020) Multi-scale progressive fusion network for single image deraining. In: Proceedings of the IEEE conference on computer vision and pattern (CVPR), pp 8346–8355
Wu H, Qu Y, Lin S, Zhou J, Qiao R, Zhang Z, Xie Y, Ma L (2021) Contrastive learning for compact single image dehazing. In: Proceedings of the IEEE conference on computer vision and pattern (CVPR), pp 10551–10560
Dong H, Pan J, Xiang L, Hu Z, Zhang X, Wang F, Yang M-H (2020) Multi-scale boosted dehazing network with dense feature fusion. In: Proceedings of the IEEE conference on computer vision and pattern (CVPR), pp 2157–2167
Wang Y, Song Y, Ma C, Zeng B (2020) Rethinking image deraining via rain streaks and vapors. In: Proceedings of the European conference on computer vision (ECCV), pp 367–382
Shao M-W, Li L, Meng D-Y, Zuo W-M (2021) Uncertainty guided multi-scale attention network for raindrop removal from a single image. IEEE Trans Image Process 30:4828–4839
Zhang L, Zhou Y, Hu X, Sun F, Duan S (2022) MSL-MNN: image deraining based on multi-scale lightweight memristive neural network. Neural Comput Appl 34:7299–7309
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. In: Proceedings of the advances in neural information processing systems (NIPS), pp 5998–6008
Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, et al (2021) An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of the international conference on learning representations (ICLR) (2021)
Liu Z, Lin Y, Cao Y, Hu H, WeiY, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE conference on computer vision (ICCV), pp 10012–10022
Wang W, Xie E, Li X, Fan D-P, Song K, Liang D, Lu T, Luo P, Shao L (2021) Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE conference on computer vision (ICCV), pp 568–578
Chen H, Wang Y, Guo T, Xu C, Deng Y, Liu Z, Ma S, Xu C, Xu C, Gao W (2021) Pre-trained image processing transformer. In: Proceedings of the IEEE conference on computer vision and pattern Recognition (CVPR), pp 12299–12310
Wang Z, Cun X, Bao J, Liu J (2022) Uformer: a general U-Shaped transformer for image restoration. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Touvron H, Cord M, Douze M, Massa F, Sablayrolles A, Jégou H (2021) Training data-efficient image transformers and distillation through attention. In: Proceedings of the international conference on machine learning (ICML). PMLR, pp 10347–10357
Haris M, Shakhnarovich G, Ukita N (2018) Deep back-projection networks for super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1664–1673
Wang X, Yu K, Dong C, Loy CC (2018) Recovering realistic texture in image super-resolution by deep spatial feature transform. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 606–615
Fu X, Huang J, Zeng D, Huang Y, Ding X, Paisley J (2017) Removing rain from single images via a deep detail network. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 3855–3863
Zhang H, Patel VM (2018) Density-aware single image de-raining using a multi-stream dense network. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 695–704
Yang W, Tan RT, Feng J, Guo Z, Yan S, Liu J (2019) Joint rain detection and removal from a single image with contextualized deep networks. IEEE Trans Pattern Anal Mach Intell 42(6):1377–1393
Deng S, Wei M, Wang J, Liang L, Xie H, Wang M (2020) DRD-Net: detail-recovery image deraining via context aggregation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 14560–14569
Gao F, Mu X, Ouyang C, Yang K, Ji S, Guo J, Wei H, Wang N, Ma L, Yang B (2022) MLTDNet: an efficient multi-level transformer network for single image deraining. Neural Comput Appl 34:14013–14027
Quan Y, Deng S, Chen Y, Ji H (2019) Deep learning for seeing through window with raindrops. In: Proceedings of the IEEE conference on computer vision (ICCV), pp 2463–2471
Quan R, Yu X, Liang Y, Yang Y (2021) Removing raindrops and rain streaks in one go. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 9147–9156
Qian R, Tan RT, Yang W, Su J, Liu J (2018) Attentive generative adversarial network for raindrop removal from a single image. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 2482–2491
Hao Z, You S, Li Y, Li K, Lu F (2019) Learning from synthetic photorealistic raindrop for single image raindrop removal. In: Proceedings of the IEEE conference on computer vision (ICCV)
Zhang K, Li D, Luo W, Ren W (2021) Dual attention-in-attention model for joint rain streak and raindrop removal. IEEE Trans Image Process 30:7608–7619
Guo T, Li X, Cherukuri V, Monga V (2019) Dense scene information estimation network for dehazing. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Guo T, Cherukuri V, Monga V (2019) Dense ‘123’ color enhancement dehazing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Shao Y, Li L, Ren W, Gao C, Sang N (2020) Domain adaptation for image dehazing. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 2808–2817
Dong J, Pan J (2020) Physics-based feature dehazing networks. In: Proceedings of the European conference on computer vision (ECCV), pp 188–204
Qin X, Wang Z, Bai Y, Xie X, Jia H (2020) FFA-Net: feature fusion attention network for single image dehazing. In: Proceedings of the AAAI conference on artificial intelligence (AAAI), vol 34, pp 11908–11915
Chen Z, Wang Y, Yang Y, Liu D (2021) PSD: principled synthetic-to-real dehazing guided by physical priors. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 7180–7189
Yi W, Dong L, Liu M, Zhao Y, Hui M, Kong L (2022) DCNet: dual-cascade network for single image dehazing. Neural Comput Appl 34:16771–16783
Chen J, Yang G, Xia M, Zhang D (2022) From depth-aware haze generation to real-world haze removal. Appl Neural Comput
Li R, Cheong L-F, Tan RT (2019) Heavy rain image restoration: integrating physics model and conditional adversarial learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1633–1642
Li R, Tan RT, Cheong L-F (2020) All in one bad weather removal using architectural search. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 3175–3185
Chen W-T, Huang Z-K, Tsai C-C, Yang H-H, Ding J-J, Kuo S-Y (2022) Learning multiple adverse weather removal via two-stage knowledge learning and multi-contrastive regularization: toward a unified model. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 17653–17662
Valanarasu JMJ, Yasarla R, Patel VM (2022) Transweather: transformer-based restoration of images degraded by adverse weather conditions. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 2353–2363
Haris M, Shakhnarovich G, Ukita N (2018) Deep back-projection networks for super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1664–1673
Liu Z-S, Wang L-W, Li, C-T, Siu W-C (2019) Hierarchical back projection network for image super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
Chen X, Huang Y, Xu L (2021) Multi-scale hourglass hierarchical fusion network for single image deraining. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 872–879
Chu X, Tian Z, Zhang B, Wang X, Wei X, Xia H, Shen C (2021) Conditional positional encodings for vision transformers. arXiv:2102.10882
Han K, Xiao A, Wu E, Guo J, Xu C, Wang Y (2021) Transformer in transformer. In: Proceedings of the advances in neural information processing systems (NIPS)
Yuan L, Chen Y, Wang T, Yu W, Shi Y, Jiang Z-H, Tay FE, Feng J, Yan S (2021) Tokens-to-token ViT: training vision transformers from scratch on ImageNet, pp 558–567
Zhao D, Li J, Li H, Xu L (2021) Hybrid local-global transformer for image dehazing. arXiv:2109.07100
Zamir SW, Arora A, Khan S, Hayat M, Khan FS, Yang M-H, Shao L (2020) Learning enriched features for real image restoration and enhancement. In: Proceedings of the European conference on computer vision (ECCV), pp 492–511
Li D, Hu J, Wang C, Li X, She Q, Zhu L, Zhang T, Chen Q (2021) Involution: inverting the inherence of convolution for visual recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 12321–12330
Xiao J, Fu X, Liu A, Wu F, Zha Z-J (2022) Image de-raining transformer. IEEE Trans Pattern Anal Mach Intell
Liu X, Ma Y, Shi Z, Chen J (2019) GridDehazeNet: attention-based multi-scale network for image dehazing. In: Proceedings of the IEEE conference on computer vision (ICCV), pp 7314–7323
Fu X, Liang B, Huang Y, Ding X, Paisley J (2019) Lightweight pyramid networks for image deraining. IEEE Trans Neural Netw Learn Syst 31(6):1794–1807
Li B, Ren W, Fu D, Tao D, Feng D, Zeng W, Wang Z (2018) Benchmarking single-image dehazing and beyond. IEEE Trans Image Process 28(1):492–505
Zhang Y, Ding L, Sharma G (2017) HazeRD: an outdoor scene dataset and benchmark for single image dehazing. In: Proceedings of the international conference on image processing (ICIP), pp 3205–3209
Ancuti C, Ancuti CO, Timofte R (2018) NTIRE 2018 challenge on image dehazing: methods and results. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 891–901
Mittal A, Soundararajan R, Bovik AC (2012) Making a “completely blind’’ image quality analyzer. IEEE Signal Process Lett 20(3):209–212
Paulson RM, Gopalakrishnan S, Mahendiran S, Srambical VP, Gopan NR (2022) A hybrid fusion-based algorithm for underwater image enhancement using fog aware density evaluator and mean saturation. In: Proceedings of the international conference on innovative computing and communication (ICICC), pp 129–140
Min X, Zhai G, Gu K, Yang X, Guan X (2018) Objective quality evaluation of dehazed images. IEEE Trans Intell Transp Syst 20(8):2879–2892
Acknowledgements
This work was supported by the National Nature Science Foundation of China under Grant 61872143.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wang, P., Zhu, H., Zhang, H. et al. LRB-T: local reasoning back-projection transformer for the removal of bad weather effects in images. Neural Comput & Applic 36, 773–789 (2024). https://doi.org/10.1007/s00521-023-09059-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-023-09059-x