Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

WaveDH: Wavelet Sub-bands Guided ConvNet for Efficient Image Dehazing (2404.01604v3)

Published 2 Apr 2024 in cs.CV and eess.IV

Abstract: The surge in interest regarding image dehazing has led to notable advancements in deep learning-based single image dehazing approaches, exhibiting impressive performance in recent studies. Despite these strides, many existing methods fall short in meeting the efficiency demands of practical applications. In this paper, we introduce WaveDH, a novel and compact ConvNet designed to address this efficiency gap in image dehazing. Our WaveDH leverages wavelet sub-bands for guided up-and-downsampling and frequency-aware feature refinement. The key idea lies in utilizing wavelet decomposition to extract low-and-high frequency components from feature levels, allowing for faster processing while upholding high-quality reconstruction. The downsampling block employs a novel squeeze-and-attention scheme to optimize the feature downsampling process in a structurally compact manner through wavelet domain learning, preserving discriminative features while discarding noise components. In our upsampling block, we introduce a dual-upsample and fusion mechanism to enhance high-frequency component awareness, aiding in the reconstruction of high-frequency details. Departing from conventional dehazing methods that treat low-and-high frequency components equally, our feature refinement block strategically processes features with a frequency-aware approach. By employing a coarse-to-fine methodology, it not only refines the details at frequency levels but also significantly optimizes computational costs. The refinement is performed in a maximum 8x downsampled feature space, striking a favorable efficiency-vs-accuracy trade-off. Extensive experiments demonstrate that our method, WaveDH, outperforms many state-of-the-art methods on several image dehazing benchmarks with significantly reduced computational costs. Our code is available at https://github.com/AwesomeHwang/WaveDH.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (72)
  1. V. A. Sindagi, P. Oza, R. Yasarla, and V. M. Patel, “Prior-based domain adaptive object detection for hazy and rainy conditions,” in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIV 16.   Springer, 2020, pp. 763–780.
  2. W.-T. Chen, I.-H. Chen, C.-Y. Yeh, H.-H. Yang, J.-J. Ding, and S.-Y. Kuo, “Sjdl-vehicle: Semi-supervised joint defogging learning for foggy vehicle re-identification,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 1, 2022, pp. 347–355.
  3. C. Sakaridis, D. Dai, and L. Van Gool, “Semantic foggy scene understanding with synthetic data,” International Journal of Computer Vision, vol. 126, pp. 973–992, 2018.
  4. E. J. McCartney, “Optics of the atmosphere: scattering by molecules and particles,” New York, 1976.
  5. B. Li, W. Ren, D. Fu, D. Tao, D. Feng, W. Zeng, and Z. Wang, “Benchmarking single-image dehazing and beyond,” IEEE Transactions on Image Processing, vol. 28, no. 1, pp. 492–505, 2018.
  6. B. Cai, X. Xu, K. Jia, C. Qing, and D. Tao, “Dehazenet: An end-to-end system for single image haze removal,” IEEE transactions on image processing, vol. 25, no. 11, pp. 5187–5198, 2016.
  7. W. Ren, S. Liu, H. Zhang, J. Pan, X. Cao, and M.-H. Yang, “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, 2016, pp. 154–169.
  8. H. Zhang and V. M. Patel, “Densely connected pyramid dehazing network,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 3194–3203.
  9. X. Yang, H. Li, Y.-L. Fan, and R. Chen, “Single image haze removal via region detection network,” IEEE Transactions on Multimedia, vol. 21, no. 10, pp. 2545–2560, 2019.
  10. S. Zhao, L. Zhang, Y. Shen, and Y. Zhou, “Refinednet: A weakly supervised refinement framework for single image dehazing,” IEEE Transactions on Image Processing, vol. 30, pp. 3391–3404, 2021.
  11. X. Liu, Y. Ma, Z. Shi, and J. Chen, “Griddehazenet: Attention-based multi-scale network for image dehazing,” in Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 7314–7323.
  12. Y. Qu, Y. Chen, J. Huang, and Y. Xie, “Enhanced pix2pix dehazing network,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 8160–8168.
  13. D. Chen, M. He, Q. Fan, J. Liao, L. Zhang, D. Hou, L. Yuan, and G. Hua, “Gated context aggregation network for image dehazing and deraining,” in 2019 IEEE winter conference on applications of computer vision (WACV).   IEEE, 2019, pp. 1375–1383.
  14. Q. Deng, Z. Huang, C.-C. Tsai, and C.-W. Lin, “Hardgan: A haze-aware representation distillation gan for single image dehazing,” in European conference on computer vision.   Springer, 2020, pp. 722–738.
  15. H. Dong, J. Pan, L. Xiang, Z. Hu, X. Zhang, F. Wang, and M.-H. Yang, “Multi-scale boosted dehazing network with dense feature fusion,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 2157–2167.
  16. X. Qin, Z. Wang, Y. Bai, X. Xie, and H. Jia, “Ffa-net: Feature fusion attention network for single image dehazing,” in Proceedings of the AAAI conference on artificial intelligence, vol. 34, no. 07, 2020, pp. 11 908–11 915.
  17. 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 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 10 551–10 560.
  18. C. Lin, X. Rong, and X. Yu, “Msaff-net: Multiscale attention feature fusion networks for single image dehazing and beyond,” IEEE transactions on multimedia, 2022.
  19. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv preprint arXiv:2010.11929, 2020.
  20. Y. Song, Z. He, H. Qian, and X. Du, “Vision transformers for single image dehazing,” IEEE Transactions on Image Processing, vol. 32, pp. 1927–1941, 2023.
  21. C.-L. Guo, Q. Yan, S. Anwar, R. Cong, W. Ren, and C. Li, “Image dehazing transformer with transmission-aware 3d position embedding,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5812–5820.
  22. 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 Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 12 802–12 813.
  23. J. Zhang and D. Tao, “Famed-net: A fast and accurate multi-scale end-to-end dehazing network,” IEEE Transactions on Image Processing, vol. 29, pp. 72–84, 2019.
  24. H. Ullah, K. Muhammad, M. Irfan, S. Anwar, M. Sajjad, A. S. Imran, and V. H. C. de Albuquerque, “Light-dehazenet: a novel lightweight cnn architecture for single image dehazing,” IEEE transactions on image processing, vol. 30, pp. 8968–8982, 2021.
  25. A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, “Mobilenets: Efficient convolutional neural networks for mobile vision applications,” arXiv preprint arXiv:1704.04861, 2017.
  26. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “Mobilenetv2: Inverted residuals and linear bottlenecks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 4510–4520.
  27. N. Ma, X. Zhang, H.-T. Zheng, and J. Sun, “Shufflenet v2: Practical guidelines for efficient cnn architecture design,” in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 116–131.
  28. M. Tan and Q. Le, “Efficientnetv2: Smaller models and faster training,” in International conference on machine learning.   PMLR, 2021, pp. 10 096–10 106.
  29. A. Howard, M. Sandler, G. Chu, L.-C. Chen, B. Chen, M. Tan, W. Wang, Y. Zhu, R. Pang, V. Vasudevan et al., “Searching for mobilenetv3,” in Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 1314–1324.
  30. K. Han, Y. Wang, Q. Tian, J. Guo, C. Xu, and C. Xu, “Ghostnet: More features from cheap operations,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 1580–1589.
  31. R. Zhang, “Making convolutional networks shift-invariant again,” in International conference on machine learning.   PMLR, 2019, pp. 7324–7334.
  32. K. He, J. Sun, and X. Tang, “Single image haze removal using dark channel prior,” IEEE transactions on pattern analysis and machine intelligence, vol. 33, no. 12, pp. 2341–2353, 2010.
  33. Q. Zhu, J. Mai, and L. Shao, “A fast single image haze removal algorithm using color attenuation prior,” IEEE transactions on image processing, vol. 24, no. 11, pp. 3522–3533, 2015.
  34. D. Berman, S. Avidan et al., “Non-local image dehazing,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 1674–1682.
  35. B. Li, X. Peng, Z. Wang, J. Xu, and D. Feng, “Aod-net: All-in-one dehazing network,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 4770–4778.
  36. S. Mallat and W. L. Hwang, “Singularity detection and processing with wavelets,” IEEE transactions on information theory, vol. 38, no. 2, pp. 617–643, 1992.
  37. A. Aballe, M. Bethencourt, F. Botana, and M. Marcos, “Using wavelets transform in the analysis of electrochemical noise data,” Electrochimica Acta, vol. 44, no. 26, pp. 4805–4816, 1999.
  38. Q. Li, L. Shen, S. Guo, and Z. Lai, “Wavelet integrated cnns for noise-robust image classification,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 7245–7254.
  39. T. Yao, Y. Pan, Y. Li, C.-W. Ngo, and T. Mei, “Wave-vit: Unifying wavelet and transformers for visual representation learning,” in European Conference on Computer Vision.   Springer, 2022, pp. 328–345.
  40. J. Yoo, Y. Uh, S. Chun, B. Kang, and J.-W. Ha, “Photorealistic style transfer via wavelet transforms,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 9036–9045.
  41. H. Huang, R. He, Z. Sun, and T. Tan, “Wavelet domain generative adversarial network for multi-scale face hallucination,” International Journal of Computer Vision, vol. 127, no. 6-7, pp. 763–784, 2019.
  42. M. Yang, Z. Wang, Z. Chi, and W. Feng, “Wavegan: Frequency-aware gan for high-fidelity few-shot image generation,” in European Conference on Computer Vision.   Springer, 2022, pp. 1–17.
  43. B. Zhang, S. Gu, B. Zhang, J. Bao, D. Chen, F. Wen, Y. Wang, and B. Guo, “Styleswin: Transformer-based gan for high-resolution image generation,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 11 304–11 314.
  44. W. Bae, J. Yoo, and J. Chul Ye, “Beyond deep residual learning for image restoration: Persistent homology-guided manifold simplification,” in Proceedings of the IEEE conference on computer vision and pattern recognition workshops, 2017, pp. 145–153.
  45. P. Liu, H. Zhang, K. Zhang, L. Lin, and W. Zuo, “Multi-level wavelet-cnn for image restoration,” in Proceedings of the IEEE conference on computer vision and pattern recognition workshops, 2018, pp. 773–782.
  46. T. Guo, H. Seyed Mousavi, T. Huu Vu, and V. Monga, “Deep wavelet prediction for image super-resolution,” in Proceedings of the IEEE conference on computer vision and pattern recognition workshops, 2017, pp. 104–113.
  47. W.-Y. Hsu and P.-W. Jian, “Detail-enhanced wavelet residual network for single image super-resolution,” IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1–13, 2022.
  48. L. Shen, Z. Yue, Q. Chen, F. Feng, and J. Ma, “Deep joint rain and haze removal from a single image,” in 2018 24th International Conference on Pattern Recognition (ICPR).   IEEE, 2018, pp. 2821–2826.
  49. H. Huang, A. Yu, Z. Chai, R. He, and T. Tan, “Selective wavelet attention learning for single image deraining,” International Journal of Computer Vision, vol. 129, pp. 1282–1300, 2021.
  50. H. Khan, M. Sharif, N. Bibi, M. Usman, S. A. Haider, S. Zainab, J. H. Shah, Y. Bashir, and N. Muhammad, “Localization of radiance transformation for image dehazing in wavelet domain,” Neurocomputing, vol. 381, pp. 141–151, 2020.
  51. W.-Y. Hsu and Y.-S. Chen, “Single image dehazing using wavelet-based haze-lines and denoising,” IEEE Access, vol. 9, pp. 104 547–104 559, 2021.
  52. O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18.   Springer, 2015, pp. 234–241.
  53. W. Shi, J. Caballero, F. Huszár, J. Totz, A. P. Aitken, R. Bishop, D. Rueckert, and Z. Wang, “Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 1874–1883.
  54. V. Dumoulin and F. Visin, “A guide to convolution arithmetic for deep learning,” arXiv preprint arXiv:1603.07285, 2016.
  55. Q. Li, L. Shen, S. Guo, and Z. Lai, “Wavecnet: Wavelet integrated cnns to suppress aliasing effect for noise-robust image classification,” IEEE Transactions on Image Processing, vol. 30, pp. 7074–7089, 2021.
  56. T. Williams and R. Li, “Wavelet pooling for convolutional neural networks,” in International conference on learning representations, 2018.
  57. Z. Hui, X. Gao, Y. Yang, and X. Wang, “Lightweight image super-resolution with information multi-distillation network,” in Proceedings of the 27th acm international conference on multimedia, 2019, pp. 2024–2032.
  58. L. Sun, J. Pan, and J. Tang, “Shufflemixer: An efficient convnet for image super-resolution,” Advances in Neural Information Processing Systems, vol. 35, pp. 17 314–17 326, 2022.
  59. Z. Li, Y. Liu, X. Chen, H. Cai, J. Gu, Y. Qiao, and C. Dong, “Blueprint separable residual network for efficient image super-resolution,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 833–843.
  60. Z. Hui, X. Wang, and X. Gao, “Fast and accurate single image super-resolution via information distillation network,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 723–731.
  61. J. Liu, J. Tang, and G. Wu, “Residual feature distillation network for lightweight image super-resolution,” in Computer Vision–ECCV 2020 Workshops: Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16.   Springer, 2020, pp. 41–55.
  62. C. Xie, X. Zhang, L. Li, H. Meng, T. Zhang, T. Li, and X. Zhao, “Large kernel distillation network for efficient single image super-resolution,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 1283–1292.
  63. C. Ancuti, C. O. Ancuti, R. Timofte, and C. De Vleeschouwer, “I-haze: A dehazing benchmark with real hazy and haze-free indoor images,” in Advanced Concepts for Intelligent Vision Systems: 19th International Conference, ACIVS 2018, Poitiers, France, September 24–27, 2018, Proceedings 19.   Springer, 2018, pp. 620–631.
  64. I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” arXiv preprint arXiv:1711.05101, 2017.
  65. ——, “Sgdr: Stochastic gradient descent with warm restarts,” arXiv preprint arXiv:1608.03983, 2016.
  66. W. Ren, L. Ma, J. Zhang, J. Pan, X. Cao, W. Liu, and M.-H. Yang, “Gated fusion network for single image dehazing,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 3253–3261.
  67. J. Dong and J. Pan, “Physics-based feature dehazing networks,” in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXX 16.   Springer, 2020, pp. 188–204.
  68. H. Bai, J. Pan, X. Xiang, and J. Tang, “Self-guided image dehazing using progressive feature fusion,” IEEE Transactions on Image Processing, vol. 31, pp. 1217–1229, 2022.
  69. Z. Tu, H. Talebi, H. Zhang, F. Yang, P. Milanfar, A. Bovik, and Y. Li, “Maxim: Multi-axis mlp for image processing,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5769–5780.
  70. M. Hong, J. Liu, C. Li, and Y. Qu, “Uncertainty-driven dehazing network,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 1, 2022, pp. 906–913.
  71. H. Li, J. Li, D. Zhao, and L. Xu, “Dehazeflow: Multi-scale conditional flow network for single image dehazing,” in Proceedings of the 29th ACM International Conference on Multimedia, 2021, pp. 2577–2585.
  72. Y. Yang, C. Wang, R. Liu, L. Zhang, X. Guo, and D. Tao, “Self-augmented unpaired image dehazing via density and depth decomposition,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 2037–2046.

Summary

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

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

Tweets