Video Quality Assessment On Msu Video Quality

Metrics

KLCC

PLCC

SRCC

Type

Results

Performance results of various models on this benchmark

Model Name	KLCC	PLCC	SRCC	Type	Paper Title	Repository
LI	0.7640	0.9270	0.9131	NR	Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception
DOVER	0.7216	0.9099	0.8871	NR	Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives
NIMA	0.6745	0.8784	0.8494	NR	NIMA: Neural Image Assessment
SPAQ MT-S	0.7186	0.8814	0.8822	NR	Perceptual Quality Assessment of Smartphone Photography
VIDEVAL	0.5414	0.7717	0.7286	NR	UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
FASTER-VQA	0.5645	0.8087	0.7508	NR	FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling
FAST-VQA	0.6498	0.8613	0.8308	NR	FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling
Y-NIQE	0.4215	0.6713	0.5985	NR	Barriers towards no-reference metrics application to compressed video quality analysis: on the example of no-reference metric NIQE	-
MDTVSFA	0.7883	0.9431	0.9289	NR	Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training
GVSP-UGCVQA-NR (multi_scale)	0.6942	0.8851	0.8673	NR	Deep Learning based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videos
PaQ-2-PiQ	0.7079	0.8549	0.8705	NR	From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality
VSFA	0.7483	0.9180	0.9049	NR	Quality Assessment of In-the-Wild Videos
MEON	0.3775	0.2898	0.5066	NR	-	-
KonCept512	0.6608	0.8464	0.8360	NR	KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment
MUSIQ	0.7433	0.9068	0.9004	NR	MUSIQ: Multi-scale Image Quality Transformer
SPAQ MT-A	0.7148	0.8824	0.8794	NR	Perceptual Quality Assessment of Smartphone Photography
UNIQUE	0.7648	0.9238	0.9148	NR	UNIQUE: Unsupervised Image Quality Estimation
DBCNN	0.7750	0.9222	0.9220	NR	Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network
LINEARITY	0.7589	0.9106	0.9104	NR	Norm-in-Norm Loss with Faster Convergence and Better Performance for Image Quality Assessment
GVSP-UGCVQA-NR (single_scale)	0.7037	0.8933	0.8742	NR	Deep Learning based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videos

0 of 21 row(s) selected.