Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 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

Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing (2403.01105v2)

Published 2 Mar 2024 in cs.CV

Abstract: Recovering a clear image from a single hazy image is an open inverse problem. Although significant research progress has been made, most existing methods ignore the effect that downstream tasks play in promoting upstream dehazing. From the perspective of the haze generation mechanism, there is a potential relationship between the depth information of the scene and the hazy image. Based on this, we propose a dual-task collaborative mutual promotion framework to achieve the dehazing of a single image. This framework integrates depth estimation and dehazing by a dual-task interaction mechanism and achieves mutual enhancement of their performance. To realize the joint optimization of the two tasks, an alternative implementation mechanism with the difference perception is developed. On the one hand, the difference perception between the depth maps of the dehazing result and the ideal image is proposed to promote the dehazing network to pay attention to the non-ideal areas of the dehazing. On the other hand, by improving the depth estimation performance in the difficult-to-recover areas of the hazy image, the dehazing network can explicitly use the depth information of the hazy image to assist the clear image recovery. To promote the depth estimation, we propose to use the difference between the dehazed image and the ground truth to guide the depth estimation network to focus on the dehazed unideal areas. It allows dehazing and depth estimation to leverage their strengths in a mutually reinforcing manner. Experimental results show that the proposed method can achieve better performance than that of the state-of-the-art approaches.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. Non-local image dehazing. In CVPR, pages 1674–1682, 2016.
  2. Air-light estimation using haze-lines. In ICCP, pages 1–9, 2017.
  3. Dehazenet: An end-to-end system for single image haze removal. IEEE Transactions on Image Processing, 25(11):5187–5198, 2016.
  4. Psd: Principled synthetic-to-real dehazing guided by physical priors. In CVPR, pages 7176–7185, 2021.
  5. Referenceless prediction of perceptual fog density and perceptual image defogging. IEEE Transactions on Image Processing, 24(11):3888–3901, 2015.
  6. Multi-scale boosted dehazing network with dense feature fusion. In CVPR, pages 2157–2167, 2020.
  7. Non-aligned supervision for real image dehazing. arXiv preprint arXiv:2303.04940, 2023.
  8. Image dehazing transformer with transmission-aware 3d position embedding. In CVPR, pages 5802–5810, 2022.
  9. Dense scene information estimation network for dehazing. In CVPRW, pages 2122–2130, 2019.
  10. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(12):2341–2353, 2010.
  11. Dsnet: Joint semantic learning for object detection in inclement weather conditions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(8):2623–2633, 2020.
  12. Adam: A method for stochastic optimization. In ICLR, 2015.
  13. Aerial image dehazing with attentive deformable transformers. In WACV, pages 6305–6314, 2023.
  14. Cnn-based simultaneous dehazing and depth estimation. In ICRA, pages 9722–9728, 2020.
  15. Benchmarking single-image dehazing and beyond. IEEE Transactions on Image Processing, 28(1):492–505, 2018.
  16. Haze transfer and feature aggregation network for real-world single image dehazing. Knowledge-Based Systems, 251:109309, 2022.
  17. Lap-net: Level-aware progressive network for image dehazing. In ICCV, pages 3194–3206, 2019.
  18. Netnet: Neighbor erasing and transferring network for better single shot object detection. In CVPR, pages 13349–13358, 2020.
  19. Multi-interactive feature learning and a full-time multi-modality benchmark for image fusion and segmentation. In CVPR, pages 8115–8124, 2023a.
  20. Learning aggregated transmission propagation networks for haze removal and beyond. IEEE Transactions on Neural Networks and Learning Systems, 30(10):2973–2986, 2019a.
  21. Griddehazenet: Attention-based multi-scale network for image dehazing. In CVPR, pages 7313–7322, 2019b.
  22. Learning deep priors for image dehazing. In ICCV, pages 2492–2500, 2019c.
  23. Nighthazeformer: Single nighttime haze removal using prior query transformer. In ACM MM, pages 4119–4128, 2023b.
  24. Earl J McCartney. Optics of the atmosphere: scattering by molecules and particles. New York, 1976.
  25. Making a “completely blind” image quality analyzer. IEEE Signal Processing Letters, 20(3):209–212, 2012.
  26. Chromatic framework for vision in bad weather. In CVPR, pages 598–605 vol.1, 2000.
  27. Vision and the atmosphere. International Journal of Computer Vision, 48:233–254, 2002.
  28. Bidnet: Binocular image dehazing without explicit disparity estimation. In CVPR, pages 5930–5939, 2020.
  29. Ffa-net: Feature fusion attention network for single image dehazing. In AAAI, pages 11908–11915, 2020.
  30. Mb-taylorformer: Multi-branch efficient transformer expanded by taylor formula for image dehazing. In ICCV, pages 12802–12813, 2023.
  31. Single image dehazing via multi-scale convolutional neural networks. In ECCV, pages 154–169, 2016.
  32. Gated fusion network for single image dehazing. In CVPR, pages 3253–3261, 2018.
  33. Mutual information-driven triple interaction network for efficient image dehazing. In ACM MM, pages 7–16, 2023.
  34. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
  35. Vision transformers for single image dehazing. IEEE Transactions on Image Processing, 32:1927–1941, 2023.
  36. Automatic recovery of the atmospheric light in hazy images. In ICCP), pages 1–11, 2014.
  37. Rethinking image restoration for object detection. NeurIPS, 35:4461–4474, 2022.
  38. Robby T Tan. Visibility in bad weather from a single image. In CVPR, pages 1–8, 2008.
  39. Maxim: Multi-axis mlp for image processing. In CVPR, pages 5769–5780, 2022.
  40. Blind image quality evaluation using perception based features. In NCC, pages 1–6, 2015.
  41. Abc-net: Avoiding blocking effect & color shift network for single image dehazing via restraining transmission bias. In ICIP, pages 1053–1057, 2020.
  42. Selfpromer: Self-prompt dehazing transformers with depth-consistency. arXiv preprint arXiv:2303.07033, 2023.
  43. Contrastive learning for compact single image dehazing. In CVPR, pages 10546–10555, 2021.
  44. Ridcp: Revitalizing real image dehazing via high-quality codebook priors. In CVPR, pages 22282–22291, 2023.
  45. Video dehazing via a multi-range temporal alignment network with physical prior. In CVPR, pages 18053–18062, 2023.
  46. Depth aware image dehazing. The Visual Computer, 38(5):1579–1587, 2022.
  47. Self-augmented unpaired image dehazing via density and depth decomposition. In CVPR, pages 2027–2036, 2022.
  48. Densely connected pyramid dehazing network. In CVPR, pages 3194–3206, 2018.
  49. Single image dehazing based on bright channel prior model and saliency analysis strategy. IET Image Processing, 15(5):1023–1031, 2021.
  50. Refinednet: A weakly supervised refinement framework for single image dehazing. IEEE Transactions on Image Processing, 30:3391–3404, 2021.
  51. Curricular contrastive regularization for physics-aware single image dehazing. In CVPR, pages 5785–5794, 2023.
  52. Physical-priors-guided dehazeformer. Knowledge-Based Systems, 266:110410, 2023.
  53. A fast single image haze removal algorithm using color attenuation prior. IEEE Transactions on Image Processing, 24(11):3522–3533, 2015.
Citations (7)
View on Semantic Scholar

Summary

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

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