keyword

full-reference image quality evaluation

Full-reference image quality evaluation is an objective measurement method in image processing that determines the perceptual quality and fidelity of a processed, degraded, or enhanced image by directly comparing it against a complete, pristine reference image considered to be the ground truth. This approach quantifies deviations such as noise, blur, compression artifacts, and structural distortions by evaluating pixel-level and perceptual discrepancies between the test image and the original benchmark. Unlike no-reference or reduced-reference methods that evaluate images without full prior knowledge, full-reference evaluation relies entirely on the availability of an ideal target, utilizing standardized mathematical and perceptual metrics such as peak signal-to-noise ratio and structural similarity index to gauge how closely an output matches the reference.

1 item

An Underwater Image Enhancement Benchmark Dataset and Beyond

Chongyi Li, Chunle Guo, Wenqi Ren, Runmin Cong, Junhui Hou, Sam Kwong, Dacheng Tao

OrganizationsBeijing Jiaotong UniversityCity University of Hong KongInstitute of Information Engineering, Chinese Academy of SciencesTianjin UniversityUniversity of Sydney

Why you should read this

Establishes a standardized real-world benchmark dataset containing 950 underwater images alongside a convolutional baseline network, Water-Net, to rigorously evaluate and advance underwater image restoration.

Underwater image enhancement has been attracting much attention due to its significance in marine engineering and aquatic robotics. Numerous underwater image enhancement algorithms have been proposed in the last few years. However, these algorithms are mainly evaluated using either synthetic datasets or few selected real-world images. It is thus unclear how these algorithms would perform on images acquired in the wild and how we could gauge the progress in the field. To bridge this gap, we present the first comprehensive perceptual study and analysis of underwater image enhancement using large-scale real-world images. In this paper, we construct an Underwater Image Enhancement Benchmark (UIEB) including 950 real-world underwater images, 890 of which have the corresponding reference images. We treat the rest 60 underwater images which cannot obtain satisfactory reference images as challenging data. Using this dataset, we conduct a comprehensive study of the state-of-the-art underwater image enhancement algorithms qualitatively and quantitatively. In addition, we propose an underwater image enhancement network (called Water-Net) trained on this benchmark as a baseline, which indicates the generalization of the proposed UIEB for training Convolutional Neural Networks (CNNs). The benchmark evaluations and the proposed Water-Net demonstrate the performance and limitations of state-of-the-art algorithms, which shed light on future research in underwater image enhancement. The dataset and code are available at this https URL.

Source

https://arxiv.org/pdf/1901.05495

Added

2026-09-18