Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Gabor-guided transformer for single image deraining (2403.07380v1)

Published 12 Mar 2024 in cs.CV and cs.AI

Abstract: Image deraining have have gained a great deal of attention in order to address the challenges posed by the effects of harsh weather conditions on visual tasks. While convolutional neural networks (CNNs) are popular, their limitations in capturing global information may result in ineffective rain removal. Transformer-based methods with self-attention mechanisms have improved, but they tend to distort high-frequency details that are crucial for image fidelity. To solve this problem, we propose the Gabor-guided tranformer (Gabformer) for single image deraining. The focus on local texture features is enhanced by incorporating the information processed by the Gabor filter into the query vector, which also improves the robustness of the model to noise due to the properties of the filter. Extensive experiments on the benchmarks demonstrate that our method outperforms state-of-the-art approaches.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. “Unsupervised single image deraining with self-supervised constraints,” in ICIP, 2019, pp. 2761–2765.
  2. “Coupling spatial and channel transformer for single image deraining,” in ICIP, 2023, pp. 2080–2084.
  3. “Removing rain from a single image via discriminative sparse coding,” in ICCV, 2015, pp. 3397–3405.
  4. “Unpaired deep image deraining using dual contrastive learning,” in CVPR, 2022, pp. 2007–2016.
  5. “Progressive image deraining networks: A better and simpler baseline,” in CVPR, 2019, pp. 3932–3941.
  6. “Multi-scale progressive fusion network for single image deraining,” in CVPR, 2020, pp. 8343–8352.
  7. “Structure-preserving deraining with residue channel prior guidance,” in ICCV, 2021, pp. 4218–4227.
  8. “Deep scale-space mining network for single image deraining,” in CVPRW, 2022, pp. 4275–4284.
  9. “Pre-trained image processing transformer,” in CVPR, 2021, pp. 12294–12305.
  10. “Transweather: Transformer-based restoration of images degraded by adverse weather conditions,” in CVPR, 2022, pp. 2343–2353.
  11. “Uformer: A general u-shaped transformer for image restoration,” in CVPR, 2022, pp. 17662–17672.
  12. “Attention is all you need,” in NeuralPS, 2017, vol. 30.
  13. “A review of convolutional neural networks and gabor filters in object recognition,” in CSCI, 2020, pp. 1560–1567.
  14. “Restormer: Efficient transformer for high-resolution image restoration,” in CVPR, 2022, pp. 5728–5739.
  15. “Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network,” in CVPR, 2016, pp. 1874–1883.
  16. “U-net: Convolutional networks for biomedical image segmentation,” in MICCAI, 2015, pp. 234–241.
  17. “Deep joint rain detection and removal from a single image,” in CVPR, 2017, pp. 1357–1366.
  18. “Removing rain from single images via a deep detail network,” in CVPR, 2017, pp. 3855–3863.
  19. He Zhang and Vishal M Patel, “Density-aware single image de-raining using a multi-stream dense network,” in CVPR, 2018, pp. 695–704.
  20. “Rain streak removal using layer priors,” in CVPR, 2016, pp. 2736–2744.
  21. “Multi-scale progressive fusion network for single image deraining,” in CVPR, 2020, pp. 8346–8355.
  22. “Progressive image deraining networks: A better and simpler baseline,” in CVPR, 2019, pp. 3937–3946.
  23. “A model-driven deep neural network for single image rain removal,” in CVPR, 2020, pp. 3103–3112.
  24. “Multi-stage progressive image restoration,” in CVPR, 2021, pp. 14821–14831.
  25. “Removing raindrops and rain streaks in one go,” in CVPR, 2021, pp. 9147–9156.
  26. “Structure-preserving deraining with residue channel prior guidance,” in CVPR, 2021, pp. 4238–4247.
  27. “Swinir: Image restoration using swin transformer,” in ICCV, 2021, pp. 1833–1844.
  28. “Image de-raining transformer,” IEEE TPAMI, 2022.
  29. “Learning a sparse transformer network for effective image deraining,” in CVPR, 2023, pp. 5896–5905.
  30. “Image-to-image translation with conditional adversarial networks,” in CVPR, 2017, pp. 1125–1134.
  31. “Compound multi-branch feature fusion for image deraindrop,” in ICIP, 2023, pp. 3399–3403.
  32. “Attentive generative adversarial network for raindrop removal from a single image,” in CVPR, 2018, pp. 2482–2491.
  33. “Deep learning for seeing through window with raindrops,” in ICCV, 2019, pp. 2463–2471.
  34. “Gabor filter-based edge detection,” Pattern recognition, vol. 25, no. 12, pp. 1479–1494, 1992.
  35. “Uformer: A general u-shaped transformer for image restoration,” in CVPR, 2022, pp. 17683–17693.
  36. “Sparse self-attention transformer for image inpainting,” Pattern Recognition, vol. 145, pp. 109897, 2024.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Sijin He (2 papers)
  2. Guangfeng Lin (8 papers)

Summary

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

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