SOTAVerified

Video Quality Assessment

Video Quality Assessment is a computer vision task aiming to mimic video-based human subjective perception. The goal is to produce a mos score, where higher score indicates better perceptual quality. Some well-known benchmarks for this task are KoNViD-1k, LIVE-VQC, YouTube-UGC and LSVQ. SROCC/PLCC/RMSE are usually used to evaluate the performance of different models.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 216 papers

TitleStatusHype
HDR-ChipQA: No-Reference Quality Assessment on High Dynamic Range Videos—0
Making Video Quality Assessment Models Robust to Bit Depth—0
Perceptual Quality Assessment of Face Video Compression: A Benchmark and An Effective MethodCode1
Zoom-VQA: Patches, Frames and Clips Integration for Video Quality AssessmentCode1
One Transform To Compute Them All: Efficient Fusion-Based Full-Reference Video Quality Assessment—0
MD-VQA: Multi-Dimensional Quality Assessment for UGC Live VideosCode1
VILA: Learning Image Aesthetics from User Comments with Vision-Language PretrainingCode0
VDPVE: VQA Dataset for Perceptual Video EnhancementCode1
MRET: Multi-resolution Transformer for Video Quality Assessment—0
Audio-Visual Quality Assessment for User Generated Content: Database and Method—0
Comparative Studies of Unsupervised and Supervised Learning Methods based on Multimedia Applications—0
Exploring Opinion-unaware Video Quality Assessment with Semantic Affinity CriterionCode1
Saliency-Aware Spatio-Temporal Artifact Detection for Compressed Video Quality Assessment—0
DDH-QA: A Dynamic Digital Humans Quality Assessment DatabaseCode0
Image quality prediction using synthetic and natural codebooks: comparative results—0
Semi-supervised Learning of Perceptual Video Quality by Generating Consistent Pairwise Pseudo-Ranks—0
Video compression dataset and benchmark of learning-based video-quality metricsCode1
Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical PerspectivesCode2
Neighbourhood Representative Sampling for Efficient End-to-end Video Quality AssessmentCode2
DCVQE: A Hierarchical Transformer for Video Quality Assessment—0
HVS Revisited: A Comprehensive Video Quality Assessment Framework—0
Panoramic Vision Transformer for Saliency Detection in 360° VideosCode1
2BiVQA: Double Bi-LSTM based Video Quality Assessment of UGC VideosCode1
Evaluating Point Cloud from Moving Camera Videos: A No-Reference MetricCode0
Learning Human Cognitive Appraisal Through Reinforcement Memory Unit—0
Shift-tolerant Perceptual Similarity MetricCode1
Exploring CLIP for Assessing the Look and Feel of ImagesCode2
Telepresence Video Quality Assessment—0
Multiview Contrastive Learning for Completely Blind Video Quality Assessment of User Generated ContentCode0
Subjective and Objective Quality Assessment of High-Motion Sports Videos at Low-BitratesCode0
Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality AssessmentCode0
FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment SamplingCode2
CONVIQT: Contrastive Video Quality EstimatorCode1
DisCoVQA: Temporal Distortion-Content Transformers for Video Quality AssessmentCode0
Perceptual Quality Assessment of Virtual Reality Videos in the WildCode0
Making Video Quality Assessment Models Sensitive to Frame Rate Distortions—0
A Framework to Map VMAF with the Probability of Just Noticeable Difference between Video Encoding Recipes—0
Deep Quality Assessment of Compressed Videos: A Subjective and Objective Study—0
A Deep Learning based No-reference Quality Assessment Model for UGC VideosCode1
Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment NetworkCode2
A crowdsourcing approach to video quality assessmentCode1
Perceptual Quality Assessment of UGC Gaming Videos—0
Visual Mechanisms Inspired Efficient Transformers for Image and Video Quality Assessment—0
Subjective and Objective Analysis of Streamed Gaming Videos—0
RankDVQA: Deep VQA based on Ranking-inspired Hybrid Training—0
A Neural Network based Framework for Effective Laparoscopic Video Quality AssessmentCode0
FAVER: Blind Quality Prediction of Variable Frame Rate VideosCode1
A strong baseline for image and video quality assessmentCode1
No-Reference Video Quality Assessment Based on Benford’s Law and Perceptual FeaturesCode0
Image Quality Assessment using Contrastive LearningCode1
Show:102550
← PrevPage 3 of 5Next →
All datasetsMSU SR-QA DatasetKoNViD-1kMSU NR VQA DatabaseLIVE-VQCMSU FR VQA DatabaseYouTube-UGCLIVE-FB LSVQLIVE-ETRILIVE LivestreamLIVE-YT-HFR

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PieAPPSROCC0.75—Unverified
2Q-Align (IQA)SROCC0.75—Unverified
3Q-Align (VQA)SROCC0.72—Unverified
4PaQ-2-PiQSROCC0.71—Unverified
5DBCNNSROCC0.69—Unverified
6MUSIQ trained on PaQ-2-PiQSROCC0.68—Unverified
7Ma-MetricSROCC0.67—Unverified
8MANIQASROCC0.67—Unverified
9ClipIQA+ ResNet50SROCC0.66—Unverified
10MUSIQ trained on SPAQSROCC0.65—Unverified
#ModelMetricClaimedVerifiedStatus
1DOVER (end-to-end)PLCC0.91—Unverified
2FasterVQA (fine-tuned)PLCC0.9—Unverified
3DOVER (head-only)PLCC0.89—Unverified
4FAST-VQA (finetuned on KonViD-1k)PLCC0.89—Unverified
5ReLaX-VQA (finetuned on KoNViD-1k)PLCC0.87—Unverified
6SimpleVQAPLCC0.86—Unverified
7DisCoVQAPLCC0.86—Unverified
8HVS-5MPLCC0.86—Unverified
9FAST-VQA (trained on LSVQ only)PLCC0.86—Unverified
10CONVIQTPLCC0.85—Unverified
#ModelMetricClaimedVerifiedStatus
1MDTVSFASRCC0.93—Unverified
2DBCNNSRCC0.92—Unverified
3UNIQUESRCC0.91—Unverified
4LISRCC0.91—Unverified
5LINEARITYSRCC0.91—Unverified
6VSFASRCC0.9—Unverified
7MUSIQSRCC0.9—Unverified
8DOVERSRCC0.89—Unverified
9SPAQ MT-SSRCC0.88—Unverified
10SPAQ BLSRCC0.88—Unverified
#ModelMetricClaimedVerifiedStatus
1ReLaX-VQA (finetuned on LIVE-VQC)PLCC0.89—Unverified
2DOVER (end-to-end)PLCC0.87—Unverified
3DOVER (head-only)PLCC0.86—Unverified
4FAST-VQA (finetuned on LIVE-VQC)PLCC0.86—Unverified
5FasterVQA (fine-tuned)PLCC0.86—Unverified
6FAST-VQA (trained on LSVQ only)PLCC0.84—Unverified
7DisCoVQAPLCC0.84—Unverified
8HVS-5MPLCC0.84—Unverified
9BVQA-2022PLCC0.84—Unverified
102BiVQAPLCC0.83—Unverified
#ModelMetricClaimedVerifiedStatus
1VMAF Y (v061)SRCC0.94—Unverified
2VMAF Y (v062)SRCC0.94—Unverified
3VMAF Y (v063)SRCC0.94—Unverified
4AHIQSRCC0.94—Unverified
5VMAF Y (v061_neg)SRCC0.91—Unverified
6VIFpSRCC0.91—Unverified
7VSISRCC0.91—Unverified
8MS-SSIMSRCC0.9—Unverified
9SR-SIMSRCC0.9—Unverified
10FSIMSRCC0.9—Unverified
#ModelMetricClaimedVerifiedStatus
1DOVER (end-to-end)PLCC0.87—Unverified
2ReLaX-VQA (finetuned on YouTube-UGC)PLCC0.87—Unverified
3DOVER (head-only)PLCC0.86—Unverified
4FasterVQA (fine-tuned)PLCC0.86—Unverified
5SimpleVQAPLCC0.86—Unverified
6FAST-VQA (finetuned on YouTube-UGC)PLCC0.85—Unverified
7HVS-5MPLCC0.85—Unverified
8ReLaX-VQA (trained on LSVQ only)PLCC0.84—Unverified
9CONVIQTPLCC0.82—Unverified
10ReLaX-VQAPLCC0.82—Unverified
#ModelMetricClaimedVerifiedStatus
1OneAlign + FAST-VQAPLCC0.9—Unverified
2DOVERPLCC0.89—Unverified
3OneAlignPLCC0.89—Unverified
4FAST-VQAPLCC0.88—Unverified
5FasterVQAPLCC0.87—Unverified
6HVS-5MPLCC0.87—Unverified
7SimpleVQAPLCC0.86—Unverified
8BVQA-2022PLCC0.85—Unverified
9DisCoVQAPLCC0.85—Unverified
10PVQPLCC0.83—Unverified
#ModelMetricClaimedVerifiedStatus
1CONVIQTSRCC0.94—Unverified
2CONTRIQUESRCC0.93—Unverified
3ChipQASRCC0.63—Unverified
4VBLIINDSSRCC0.48—Unverified
5ChipQA-0SRCC0.4—Unverified
6BRISQUESRCC0.27—Unverified
7TLVQMSRCC0.23—Unverified
#ModelMetricClaimedVerifiedStatus
1ChipQASRCC0.76—Unverified
2ChipQA-0SRCC0.75—Unverified
3TLVQMSRCC0.75—Unverified
4RAPIQUESRCC0.74—Unverified
#ModelMetricClaimedVerifiedStatus
1ST-GREEDSRCC0.88—Unverified
2GREED-VMAFSRCC0.87—Unverified
3GSTISRCC0.81—Unverified