PUGCQ: A Large Scale Dataset for Quality Assessment of Professional User-Generated Content

Guo, Li; Chen, Baoliang; Zhu, Lingyu; He, Qinwen; Fan, Hongfei; Wang, Shiqi

doi:10.1145/3474085.3475183

Cited by 2 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the disadvantage of subjective IQA is that actual deployment is slow, and it cannot optimize a system in real‐time 25 . To quickly evaluate an image in real‐time, a mathematical model that simulates human vision, an objective IQA model has been proposed 26 . Objective IQA can be divided into three categories: FR, RR, and NR IQA 27 …”

Section: Related Workmentioning

confidence: 99%

“…25 To quickly evaluate an image in real-time, a mathematical model that simulates human vision, an objective IQA model has been proposed. 26 Objective IQA can be divided into three categories: FR, RR, and NR IQA. 27 A method that can obtain an undistorted original image and predict the quality score of the distorted image by comparing the difference between the distorted image and the original image is an FR-IQA method.…”

Section: Image-quality Assessmentmentioning

confidence: 99%

See 1 more Smart Citation

Contrastive distortion‐level learning‐based no‐reference image‐quality assessment

Wei

Zhou

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

A contrastive distortion-level learning-based no-reference image-quality assessment (NR-IQA) framework is proposed in this study to further effectively model various distortion types with the same or different distortion levels.The proposed method aims to improve the prediction accuracy of NR-IQA. The proposed method consists of three parts: multiscale distortion-level representation learning, single-image NR-IQA, and a representation affinity module, which can reduce NR-IQA computational complexity while maintaining a low-distortion representation of high-distortion inputs. The proposed NR-IQA method aims to extract distributional features of samples in real distorted images and predict ambiguity based on distortion-level learning. Experimental results show that by comparing on many NR-IQA data sets the proposed method can outperform state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%