Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 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

SynFog: A Photo-realistic Synthetic Fog Dataset based on End-to-end Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving (2403.17094v1)

Published 25 Mar 2024 in cs.CV and cs.LG

Abstract: To advance research in learning-based defogging algorithms, various synthetic fog datasets have been developed. However, existing datasets created using the Atmospheric Scattering Model (ASM) or real-time rendering engines often struggle to produce photo-realistic foggy images that accurately mimic the actual imaging process. This limitation hinders the effective generalization of models from synthetic to real data. In this paper, we introduce an end-to-end simulation pipeline designed to generate photo-realistic foggy images. This pipeline comprehensively considers the entire physically-based foggy scene imaging process, closely aligning with real-world image capture methods. Based on this pipeline, we present a new synthetic fog dataset named SynFog, which features both sky light and active lighting conditions, as well as three levels of fog density. Experimental results demonstrate that models trained on SynFog exhibit superior performance in visual perception and detection accuracy compared to others when applied to real-world foggy images.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (57)
  1. D-hazy: A dataset to evaluate quantitatively dehazing algorithms. In IEEE International Conference on Image Processing, pages 2226–2230, 2016.
  2. O-haze: a dehazing benchmark with real hazy and haze-free outdoor images. In IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 754–762, 2018.
  3. Dense-haze: A benchmark for image dehazing with dense-haze and haze-free images. In IEEE International Conference on Image Processing, pages 1014–1018, 2019.
  4. Nh-haze: An image dehazing benchmark with non-homogeneous hazy and haze-free images. In IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 444–445, 2020.
  5. Seeing through fog without seeing fog: Deep multimodal sensor fusion in unseen adverse weather. In IEEE Conference on Computer Vision and Pattern Recognition, pages 11682–11692, 2020.
  6. A review of computer vision techniques for the analysis of urban traffic. IEEE Transactions on Intelligent Transportation Systems, 12(3):920–939, 2011.
  7. Ting Chen. Digital camera system simulator and applications. Stanford University, 2003.
  8. Referenceless prediction of perceptual fog density and perceptual image defogging. IEEE Transactions on Image Processing, 24(11):3888–3901, 2015.
  9. The cityscapes dataset for semantic urban scene understanding. In IEEE Conference on Computer Vision and Pattern Recognition, pages 3213–3223, 2016.
  10. Satellite image classification via two-layer sparse coding with biased image representation. IEEE Geoscience and Remote Sensing Letters, 8(1):173–176, 2010.
  11. Curriculum model adaptation with synthetic and real data for semantic foggy scene understanding. International Journal of Computer Vision, 128:1182–1204, 2020.
  12. Multi-scale boosted dehazing network with dense feature fusion. In IEEE Conference on Computer Vision and Pattern Recognition, pages 2157–2167, 2020.
  13. Influence of the atmosphere on optical systems. Optica Acta, 1970.
  14. Objective quality evaluation of dehazed images. TITS, 2018.
  15. Image systems simulation. Handbook of Digital Imaging, 1:373–400, 2015.
  16. A simulation tool for evaluating digital camera image quality. In Image Quality and System Performance, pages 124–131. SPIE, 2003.
  17. Digital camera simulation. Applied Optics, 51(4):A80–A90, 2012.
  18. Virtual worlds as proxy for multi-object tracking analysis. In IEEE Conference on Computer Vision and Pattern Recognition, pages 4340–4349, 2016.
  19. Semantic understanding of foggy scenes with purely synthetic data. In IEEE Intelligent Transportation Systems Conference (ITSC), pages 3675–3681, 2019.
  20. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(12):2341–2353, 2010.
  21. Diffuse radiation in the galaxy. Astrophysical Journal, vol. 93, p. 70-83 (1941)., 93:70–83, 1941.
  22. Ultralytics yolo, 2023.
  23. Kyung Won Kim. The comparison of visibility measurement between image-based visual range, human eye-based visual range, and meteorological optical range. Atmospheric Environment, 190:74–86, 2018.
  24. Optik. Springer-Verlag, 2013.
  25. Benchmarking single-image dehazing and beyond. IEEE Transactions on Image Processing, 28(1):492–505, 2018.
  26. Realistic large-scale fine-depth dehazing dataset from 3d videos. arXiv preprint arXiv:2004.08554, 2020.
  27. Learning depth from single monocular images using deep convolutional neural fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(10):2024–2039, 2015.
  28. Griddehazenet: Attention-based multi-scale network for image dehazing. In IEEE International Conference on Computer Vision, pages 7314–7323, 2019a.
  29. Nighttime image dehazing based on variational decomposition model. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 640–649, 2022.
  30. Soft prototyping camera designs for car detection based on a convolutional neural network. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, pages 0–0, 2019b.
  31. A system for generating complex physically accurate sensor images for automotive applications. arXiv preprint arXiv:1902.04258, 2019c.
  32. Validation of physics-based image systems simulation with 3-d scenes. IEEE Sensors Journal, 22(20):19400–19410, 2022.
  33. Earl J McCartney. Optics of the atmosphere: scattering by molecules and particles. New York, 1976.
  34. Vision and the atmosphere. International Journal of Computer Vision, 48:233–254, 2002.
  35. A multi-purpose realistic haze benchmark with quantifiable haze levels and ground truth. IEEE Transactions on Image Processing, 2023.
  36. National Standards of People’s Republic of China. Grade of fog forecast, 2011.
  37. Roberto Nebuloni. Empirical relationships between extinction coefficient and visibility in fog. Applied Optics, 44(18):3795–3804, 2005.
  38. Physically based rendering: From theory to implementation. MIT Press, 2023.
  39. Ffa-net: Feature fusion attention network for single image dehazing. In AAAI, pages 11908–11915, 2020.
  40. Semantic foggy scene understanding with synthetic data. International Journal of Computer Vision, 126:973–992, 2018.
  41. High-accuracy stereo depth maps using structured light. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages I–I. IEEE, 2003.
  42. Indoor segmentation and support inference from rgbd images. In European Conference on Computer Vision, pages 746–760. Springer, 2012.
  43. Vision transformers for single image dehazing. IEEE Transactions on Image Processing, 32:1927–1941, 2023.
  44. Shift: a synthetic driving dataset for continuous multi-task domain adaptation. In IEEE Conference on Computer Vision and Pattern Recognition, pages 21371–21382, 2022.
  45. Investigating haze-relevant features in a learning framework for image dehazing. In IEEE Conference on Computer Vision and Pattern Recognition, pages 2995–3000, 2014.
  46. Improved visibility of road scene images under heterogeneous fog. In IEEE Intelligent Vehicles Symposium, pages 478–485, 2010.
  47. Vision enhancement in homogeneous and heterogeneous fog. IEEE Intelligent Transportation Systems Magazine, 4(2):6–20, 2012.
  48. Resolution loss without imaging blur. JOSA A, 29(8):1516–1528, 2012.
  49. Procedural modeling and physically based rendering for synthetic data generation in automotive applications. arXiv preprint arXiv:1710.06270, 2017.
  50. Contrastive learning for compact single image dehazing. In IEEE Conference on Computer Vision and Pattern Recognition, pages 10551–10560, 2021.
  51. Nighttime dehazing with a synthetic benchmark. In Proceedings of the ACM International Conference on Multimedia, pages 2355–2363, 2020.
  52. Vision-based parking-slot detection: A dcnn-based approach and a large-scale benchmark dataset. IEEE Transactions on Image Processing, 27(11):5350–5364, 2018a.
  53. Simulation of atmospheric visibility impairment. IEEE Transactions on Image Processing, 30:8713–8726, 2021.
  54. The unreasonable effectiveness of deep features as a perceptual metric. In IEEE Conference on Computer Vision and Pattern Recognition, pages 586–595, 2018b.
  55. Hazerd: an outdoor scene dataset and benchmark for single image dehazing. In IEEE International Conference on Image Processing, pages 3205–3209, 2017.
  56. Dehazing evaluation: Real-world benchmark datasets, criteria, and baselines. IEEE Transactions on Image Processing, 29:6947–6962, 2020.
  57. A fast single image haze removal algorithm using color attenuation prior. IEEE Transactions on Image Processing, 24(11):3522–3533, 2015.
Citations (1)
View on Semantic Scholar

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