SynthRSF: A Novel Photorealistic Synthetic Dataset for Adverse Weather Condition Denoising

Angelos Kanlis, Vazgken Vanian, Sotiris Karvarsamis, Ioanna Gkika, Konstantinos Konstantoudakis, Dimitrios Zarpalas

2024

Abstract

This paper presents the SynthRSF dataset for training and evaluating single-image rain, snow and haze denoising algorithms, as well as evaluating object detection, semantic segmentation, and depth estimation performance in noisy or denoised images. Our dataset features 26,893 noisy images, each accompanied by its corresponding ground truth image. It further includes 13,800 noisy images accompanied by ground truth, 16-bit depth maps and pixel-accurate annotations for various object instances in each frame. The utility of SynthRSF is assessed by training unified models for rain, snow, and haze removal, achieving good objective metrics and excellent subjective results compared to existing adverse weather condition datasets. Furthermore, we demonstrate its use as a benchmark for the performance of an object detection algorithm in weather-degraded image datasets.

Paper Citation

in Harvard Style

Kanlis A., Vanian V., Karvarsamis S., Gkika I., Konstantoudakis K. and Zarpalas D. (2024). SynthRSF: A Novel Photorealistic Synthetic Dataset for Adverse Weather Condition Denoising. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 567-574. DOI: 10.5220/0012397700003660

in Bibtex Style

@conference{visapp24,
author={Angelos Kanlis and Vazgken Vanian and Sotiris Karvarsamis and Ioanna Gkika and Konstantinos Konstantoudakis and Dimitrios Zarpalas},
title={SynthRSF: A Novel Photorealistic Synthetic Dataset for Adverse Weather Condition Denoising},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={567-574},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012397700003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - SynthRSF: A Novel Photorealistic Synthetic Dataset for Adverse Weather Condition Denoising
SN - 978-989-758-679-8
AU - Kanlis A.
AU - Vanian V.
AU - Karvarsamis S.
AU - Gkika I.
AU - Konstantoudakis K.
AU - Zarpalas D.
PY - 2024
SP - 567
EP - 574
DO - 10.5220/0012397700003660
PB - SciTePress