Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 172 tok/s
Gemini 2.5 Pro 48 tok/s Pro
GPT-5 Medium 30 tok/s Pro
GPT-5 High 29 tok/s Pro
GPT-4o 103 tok/s Pro
Kimi K2 199 tok/s Pro
GPT OSS 120B 464 tok/s Pro
Claude Sonnet 4.5 36 tok/s Pro
2000 character limit reached

Parallel Cross Strip Attention Network for Single Image Dehazing (2405.05811v1)

Published 9 May 2024 in cs.CV

Abstract: The objective of single image dehazing is to restore hazy images and produce clear, high-quality visuals. Traditional convolutional models struggle with long-range dependencies due to their limited receptive field size. While Transformers excel at capturing such dependencies, their quadratic computational complexity in relation to feature map resolution makes them less suitable for pixel-to-pixel dense prediction tasks. Moreover, fixed kernels or tokens in most models do not adapt well to varying blur sizes, resulting in suboptimal dehazing performance. In this study, we introduce a novel dehazing network based on Parallel Stripe Cross Attention (PCSA) with a multi-scale strategy. PCSA efficiently integrates long-range dependencies by simultaneously capturing horizontal and vertical relationships, allowing each pixel to capture contextual cues from an expanded spatial domain. To handle different sizes and shapes of blurs flexibly, We employs a channel-wise design with varying convolutional kernel sizes and strip lengths in each PCSA to capture context information at different scales.Additionally, we incorporate a softmax-based adaptive weighting mechanism within PCSA to prioritize and leverage more critical features.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Image enhancement using multi scale image features extracted by top-hat transform. Optics & Laser Technology 44, 2 (2012), 328–336.
  2. Non-local image dehazing. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1674–1682.
  3. Dehazenet: An end-to-end system for single image haze removal. IEEE transactions on image processing 25, 11 (2016), 5187–5198.
  4. End-to-end object detection with transformers. In European conference on computer vision. Springer, 213–229.
  5. Msp-former: Multi-scale projection transformer for single image desnowing. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1–5.
  6. Domain adaptive faster r-cnn for object detection in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3339–3348.
  7. Selective frequency network for image restoration. In The Eleventh International Conference on Learning Representations.
  8. Multi-scale boosted dehazing network with dense feature fusion. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2157–2167.
  9. Image dehazing transformer with transmission-aware 3d position embedding. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 5812–5820.
  10. Single image haze removal using dark channel prior. IEEE transactions on pattern analysis and machine intelligence 33, 12 (2010), 2341–2353.
  11. Distilling image dehazing with heterogeneous task imitation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 3462–3471.
  12. Multi-scale enhanced graph convolutional network for mild cognitive impairment detection. Pattern Recognition 134 (2023), 109106.
  13. Aod-net: All-in-one dehazing network. In Proceedings of the IEEE international conference on computer vision. 4770–4778.
  14. End-to-end united video dehazing and detection. In Proceedings of the AAAI conference on artificial intelligence, Vol. 32.
  15. Benchmarking single-image dehazing and beyond. IEEE Transactions on Image Processing 28, 1 (2018), 492–505.
  16. Benchmarking Single-Image Dehazing and Beyond. IEEE Trans. Image Process. 28, 1 (2019), 492–505.
  17. Swinir: Image restoration using swin transformer. In Proceedings of the IEEE/CVF international conference on computer vision. 1833–1844.
  18. Msaff-net: Multiscale attention feature fusion networks for single image dehazing and beyond. IEEE transactions on multimedia (2022).
  19. Griddehazenet: Attention-based multi-scale network for image dehazing. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 7314–7323.
  20. From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data. arXiv preprint arXiv:2108.02934 (2021).
  21. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision. 10012–10022.
  22. Deep residual fourier transformation for single image deblurring. arXiv preprint arXiv:2111.11745 2, 3 (2021), 5.
  23. FFA-Net: Feature fusion attention network for single image dehazing. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34. 11908–11915.
  24. MB-TaylorFormer: Multi-branch efficient transformer expanded by Taylor formula for image dehazing. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 12802–12813.
  25. Enhanced pix2pix dehazing network. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 8160–8168.
  26. Single image dehazing via multi-scale convolutional neural networks. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14. Springer, 154–169.
  27. Model adaptation with synthetic and real data for semantic dense foggy scene understanding. In Proceedings of the european conference on computer vision (ECCV). 687–704.
  28. Semantic foggy scene understanding with synthetic data. International Journal of Computer Vision 126 (2018), 973–992.
  29. Domain adaptation for image dehazing. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2808–2817.
  30. Improved YOLOv3 model with feature map cropping for multi-scale road object detection. Measurement Science and Technology 34, 4 (2023), 045406.
  31. Robby T Tan. 2008. Visibility in bad weather from a single image. In 2008 IEEE conference on computer vision and pattern recognition. IEEE, 1–8.
  32. Training data-efficient image transformers & distillation through attention. In International conference on machine learning. PMLR, 10347–10357.
  33. Stripformer: Strip transformer for fast image deblurring. In European Conference on Computer Vision. Springer, 146–162.
  34. Maxim: Multi-axis mlp for image processing. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 5769–5780.
  35. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In Proceedings of the IEEE/CVF international conference on computer vision. 568–578.
  36. Uformer: A general u-shaped transformer for image restoration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 17683–17693.
  37. Contrastive learning for compact single image dehazing. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 10551–10560.
  38. Perceiving and modeling density is all you need for image dehazing. arXiv preprint arXiv:2111.09733 (2021).
  39. Restormer: Efficient transformer for high-resolution image restoration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 5728–5739.
  40. He Zhang and Vishal M Patel. 2018. Densely connected pyramid dehazing network. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3194–3203.
  41. Deep image deblurring: A survey. International Journal of Computer Vision 130, 9 (2022), 2103–2130.
  42. Pyramid channel-based feature attention network for image dehazing. Computer Vision and Image Understanding 197 (2020), 103003.
  43. Biformer: Vision transformer with bi-level routing attention. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 10323–10333.
  44. Single image dehazing using color attenuation prior.. In BMVC. Citeseer, 1–10.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets

This paper has been mentioned in 1 tweet and received 0 likes.

Upgrade to Pro to view all of the tweets about this paper:

Start a free 7-day Pro trial