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
Advancing Video Quality Assessment for AIGC—0
Revisiting Video Quality Assessment from the Perspective of GeneralizationCode0
LMM-VQA: Advancing Video Quality Assessment with Large Multimodal ModelsCode0
Subjective and Objective Quality Assessment of Rendered Human Avatar Videos in Virtual Reality—0
BVI-UGC: A Video Quality Database for User-Generated Content Transcoding—0
Benchmarking Multi-dimensional AIGC Video Quality Assessment: A Dataset and Unified ModelCode0
Highly Efficient No-reference 4K Video Quality Assessment with Full-Pixel Covering Sampling and Training Strategy—0
CLIPVQA:Video Quality Assessment via CLIPCode0
Priorformer: A UGC-VQA Method with content and distortion priors—0
VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation—0
MVAD: A Multiple Visual Artifact Detector for Video Streaming—0
PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild—0
RMT-BVQA: Recurrent Memory Transformer-based Blind Video Quality Assessment for Enhanced Video Content—0
NTIRE 2024 Quality Assessment of AI-Generated Content Challenge—0
AIS 2024 Challenge on Video Quality Assessment of User-Generated Content: Methods and ResultsCode0
PCQA: A Strong Baseline for AIGC Quality Assessment Based on Prompt Condition—0
Study of the effect of Sharpness on Blind Video Quality Assessment—0
Learned Scanpaths Aid Blind Panoramic Video Quality AssessmentCode0
Perceptual Video Quality Assessment: A Survey—0
Video Quality Assessment Based on Swin TransformerV2 and Coarse to Fine Strategy—0
Knowledge Guided Semi-Supervised Learning for Quality Assessment of User Generated VideosCode0
Q-Boost: On Visual Quality Assessment Ability of Low-level Multi-Modality Foundation Models—0
Full-reference Video Quality Assessment for User Generated Content Transcoding—0
RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment—0
CLiF-VQA: Enhancing Video Quality Assessment by Incorporating High-Level Semantic Information related to Human Feelings—0
Geometry-Aware Video Quality Assessment for Dynamic Digital Human—0
Video Quality Assessment and Coding Complexity of the Versatile Video Coding Standard—0
UGC Quality Assessment: Exploring the Impact of Saliency in Deep Feature-Based Quality AssessmentCode0
Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessment—0
Capturing Co-existing Distortions in User-Generated Content for No-reference Video Quality Assessment—0
NTIRE 2023 Quality Assessment of Video Enhancement Challenge—0
Subjective and Objective Audio-Visual Quality Assessment for User Generated ContentCode0
StarVQA+: Co-training Space-Time Attention for Video Quality AssessmentCode0
Blind Video Quality Assessment at the Edge—0
Study of Subjective and Objective Quality Assessment of Mobile Cloud Gaming Videos—0
SB-VQA: A Stack-Based Video Quality Assessment Framework for Video Enhancement—0
SR+Codec: a Benchmark of Super-Resolution for Video Compression Bitrate ReductionCode0
GAMIVAL: Video Quality Prediction on Mobile Cloud Gaming ContentCode0
HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular content—0
HDR-ChipQA: No-Reference Quality Assessment on High Dynamic Range Videos—0
Making Video Quality Assessment Models Robust to Bit Depth—0
One Transform To Compute Them All: Efficient Fusion-Based Full-Reference Video Quality Assessment—0
VILA: Learning Image Aesthetics from User Comments with Vision-Language PretrainingCode0
MRET: Multi-resolution Transformer for Video Quality Assessment—0
Comparative Studies of Unsupervised and Supervised Learning Methods based on Multimedia Applications—0
Audio-Visual Quality Assessment for User Generated Content: Database and Method—0
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
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 (v063)SRCC0.94—Unverified
2VMAF Y (v061)SRCC0.94—Unverified
3VMAF Y (v062)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