SynFog: A Photo-Realistic Synthetic Fog Dataset Based on End-to-End Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving
Abstract
To advance research in learning-based defogging algorithms various synthetic fog datasets have been developed. However exsiting 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.
Cite
Text
Xie et al. "SynFog: A Photo-Realistic Synthetic Fog Dataset Based on End-to-End Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving." Conference on Computer Vision and Pattern Recognition, 2024. doi:10.1109/CVPR52733.2024.02056Markdown
[Xie et al. "SynFog: A Photo-Realistic Synthetic Fog Dataset Based on End-to-End Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving." Conference on Computer Vision and Pattern Recognition, 2024.](https://mlanthology.org/cvpr/2024/xie2024cvpr-synfog/) doi:10.1109/CVPR52733.2024.02056BibTeX
@inproceedings{xie2024cvpr-synfog,
title = {{SynFog: A Photo-Realistic Synthetic Fog Dataset Based on End-to-End Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving}},
author = {Xie, Yiming and Wei, Henglu and Liu, Zhenyi and Wang, Xiaoyu and Ji, Xiangyang},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2024},
pages = {21763-21772},
doi = {10.1109/CVPR52733.2024.02056},
url = {https://mlanthology.org/cvpr/2024/xie2024cvpr-synfog/}
}