Evaluation of Defogging: A Real-World Benchmark Dataset, A New Criterion and Baselines

Modern defogging methods are able to achieve very comparable results whose differences are too subtle for people to qualitatively judge. On the other hand, existing quantitative evaluation methods are also not convincing due to a lack of proper datasets. In this work, we attempt to address these iss...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhao, Shiyu, Zhang, Lin, Huang, Shuaiyi, Shen, Ying, Zhao, Shengjie, Yang, Yukai
Format: Conference Proceeding
Language:English
Subjects:
Benchmark dataset for defogging evaluation
Benchmark testing
FR-IQA
Image edge detection
Image quality
Image restoration
Measurement
metric for defogging evaluation
Pipelines
Urban areas
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Modern defogging methods are able to achieve very comparable results whose differences are too subtle for people to qualitatively judge. On the other hand, existing quantitative evaluation methods are also not convincing due to a lack of proper datasets. In this work, we attempt to address these issues and establish a long-term lacking benchmark dataset, namely BeDDE (BEnchmark Dataset for Defogging Evaluation), for evaluating the performance of defogging algorithms. To our knowledge, BeDDE is the first real-world dataset comprising foggy images with their registered clear counterparts. Using BeDDE, we set up a new criterion for evaluating defogging methods where VSI, a full reference image quality assessment metric, is calculated and averaged on registered ROIs of all image pairs. The evaluation results of the proposed criterion correlate well with human judgements. 10 state-of-the-art defogging methods are evaluated as baselines on BeDDE. BeDDE is available online.
ISSN:1945-788X
DOI:10.1109/ICME.2019.00316