会议论文

Chen, JY

英文

International Conference on Image Processing. Proceedings

1522-4880

2022

11-15

IEEE International Conference on Image Processing (ICIP)

IEEE International Conference on Image Processing ICIP

OCT 16-19, 2022

Bordeaux, FRANCE

[Chen, Jiyou;Yang, Gaobo] Hunan Univ, Sch Comp Sci & Elect Engn, Changsha 410082, Peoples R China.^[Chen, Jiyou] Hengyang Normal Univ, Sch Phys & Elect Engn, Hengyang 421008, Peoples R China.^[Wang, Shengchun] Hunan Normal Univ, Sch Informat Sci & Engn, Changsha 410081, Peoples R China.^[Liu, Xin] Hunan Appl Technol Univ, Changde 415100, Peoples R China.

The Institute of Electrical and Electronics Engineers Signal Processing Society

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

978-1-6654-9620-9

10.1109/ICIP46576.2022.9897706

National Natural Science Foundation of China [61972143, 61972142]; Scientific Research Fund of Hunan Provincial Education Department [21C0534]; Scientific Research Fund of Hunan Provincial Key Laboratory of Intelligent Information Processing and Application [2021HSKFJJ040]

本校为通讯机构

Most existing image dehazing approaches are able to achieve desirable results whose differences are too subtle for people to qualitatively judge. Therefore, it is important to adopt quantitative assessment on real-world hazy images. However, many dehazing works have not been quantitatively evaluated on real-world hazy images due to the lack of appropriate real-world datasets. In this work, we attempt to address the issue and present a well-aligned real-world benchmark dataset, namely RW-Haze, for image dehazing evaluation, which had been lackin...