VMAF reproducibility: Validating a perceptual practical video quality metric
The DOI matches its Crossref record; 3 of the 5 references it cites were found in a registry or an index.
Abstract
Measuring video quality with standard metrics ensures that operators can deliver to consumers the desired quality of experience (QoE) at an optimal cost. Such metrics also allow CODEC engineers to optimize the performance of their encoding algorithms. This paper briefly surveys existing video quality metrics and then presents results of the new Video Multi-Method Assessment Fusion (VMAF) metric [1] proposed by Netflix. The author and colleagues used VMAF to measure the quality of a 4K dataset encoded with the RealMedia video CODEC at a range of bitrates. They also gathered subjective quality assessments from a group of viewers for the same dataset. The paper presents findings of correlation between subjective and objective results.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892
ON BETWEEN-COEFFICIENT CONTRAST MASKING OF DCT BASIS FUNCTIONS
Ponomarenko, N. N., Silvestri, F., Egiazarian, K., Carli, M., Astola, J. T., & Лукин, В. В. (2007) · Cited by 364
Measuring video quality in the network: from quality of service to user experience
Staelens, N. (2015) · Ghent University Academic Bibliography (Ghent University) · Cited by 15
Research works printed but not linked: 3
- 0, Elementa
- 0, Methodology for the subjective assessment of the quality of television pictures, ITU-R Recommendation BT 500
- li, 2016, Toward A Practical Perceptual Video Quality Metric, Netflix TechBlog June
Cited by
Items 201–222 of 222
Janus Streamer: A Scalable WebRTC Media Streaming Server
Park, J., Jeong, S., Kim, S. M., & Kim, J. (2026) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc65079.2026.11366482 · Cited by 1
“QoE was assessed using three criteria: a VMAF score above 93 [31], audio jitter below 40 ms, and a packet loss rate under 1%.”
WebRTC-StallQuant: In-Band, Tag-Free Estimation of Stall-Duration Distributions for QoE
Yin, Z., Li, X., Xu, H., et al. (2025) · International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · doi:10.1109/icaice68195.2025.11382232
“For example, [3] uses pause events to forecast playback quality, [4] infers VMAF from bitrate, and Alibaba's work[5] evaluates a new conferencing architecture (GSO-Simulcast) using average video/voice stalling and frame rate.”
Relatively Robust QoS and QoE Score Aggregation
Weber, T. A. (2025) · International Conference on Applied Computational Intelligence in Information Systems (ACIIS) · doi:10.1109/aciis66255.2025.11402948
“Restrictions apply. has demonstrated strong correlation with MOS ratings [27].”
Rate Control for 360$^{\circ }$ Versatile Video Coding Based on Visual Gaze Mechanism
Zhao, Z., Wang, M., Sui, X., Chen, P., He, X., & Wang, S. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3668626
Lightweight Hardware Design of a Chaos-Based Stream Cipher for Secure Video Applications
Gautier, G. (2020) · theses.fr (ABES) · doi:10.70675/68678ff1z88b6z425azafa6zb1d94b72bcb7 · Cited by 1
DRL-Based Edge Caching for 360-Degree Video in Broadband Delivery of TV 3.0
Li, C., & Song, M. (2026) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2026.3679933
“To evaluate video quality, we use the video multi-method assessment fusion (VMAF) metric, which is widely accepted for video quality evaluation and can be e ff ectively applied to 360-degree videos [25].”
Deep learning-assisted video list decoding in error-prone video transmission systems
Zhang, Y. (2024) · theses.fr (ABES) · doi:10.70675/1d0878eez4905z432az9623zbee74e1a454f
PivotSketch: Control-Ready Semantic Ranking for Adaptive Video Streaming
Zhang, S., Li, Y., Zhang, C., Fan, X., Hu, X., & Duan, H. (2026) · International Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV) · doi:10.1145/3798065.3798086
“For 𝑐 𝑖 , let 𝑆 𝑖,𝑟 and 𝑄 𝑖,𝑟 be the encoded size and perceptual quality (e.g., VMAF [13]) of chunk 𝑖 at representation 𝑟 .”
Zero-Latency strategies for video transmission using frame extrapolation
Kanj, H. (2024) · theses.fr (ABES) · doi:10.70675/05e83c11zf4f3z432bz87c1zc120499c3509
Breath: Adaptive Protection Boundary in FEC Encoding for Mobile Real-Time Video Streaming
Huang, S., Lv, G., Zhao, Y., et al. (2026) · ACM Web Conference (WWW) · doi:10.1145/3774904.3792265
An efficient video quality assessment model incorporating VideoMamba and dual-dimensional attention
Zeng, H., Liu, F., Cui, Z., Gan, Z., & Tang, G. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02416-5
Fed-MVP: Federated Multi-Homing Video Streaming Protocol
Sepahi, A., Cai, L., Yang, W., et al. (2026) · IEEE Transactions on Networking · doi:10.1109/ton.2026.3701659
“VMAF, developed by Netflix, uses machine learning for content-dependent assessments, providing scores on a 0 to 100 scale [50].”
Figuerola, C. T., Signoret, C., Holmer, E., & Andin, J. (2026) · Scientific Reports · doi:10.1038/s41598-026-57531-0
“While the auditory modality is heavily reliant on SNR, the visual modality lacks a robust metric of video quality 44,45 because of the complexities of the visual signal (e.g., contrast, color, saturation, orientation of the object, etc.).”
UVCG: Leveraging Temporal Consistency for Video Protection Against Stable-Diffusion-Based Editing
Li, K., Cao, J., He, L., Yu, X., & Zhang, X.-P. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3705351
“To quantify differences between protected and unprotected videos, we further calculate SSIM [17], PSNR, LPIPS [18], and VMAF [19], averaging scores across frame pairs.”
Streaming video QoE assessment method combining hybrid feature fusion and adaptive buffer sampling
Li, H., Kong, G., Duan, X., et al. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05507-y
Gakumi, R., Masaki, H., & Harada, H. (2026) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2026.3708422
“In practice, scores are often interpreted as excellent ( ≥ 90), good (80–90), or fair (70–80) [20].”
A Siamese Neural Network-Based Perceptual Quality Metric for Image and Video Assessment
Toprak, A. G., Mercan, Ö. B., & Özdem, M. (2026) · Sivas Cumhuriyet Üniversitesi Bilim ve Teknoloji Dergisi. · doi:10.69560/cujast.1843247
Relevancy-Guided Adaptive Decoupling for Multi-Module Joint Optimization in Perceptual Video Coding
Shi, Y., Yin, H., Xie, Y., Wang, X., Wang, H., & Huang, X. (2026) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2026.3705501
“Techniques like spatial masking and temporal modulation [8], [9], [10], [11] are increasingly evaluated by advanced metrics like VMAF [12].”
PS-TTS: Phonetic Synchronization in Text-To-Speech for Achieving Natural Automated Dubbing
Hong, C., Song, Y., Park, H., Bang, C., Gu, D., Lee, D. H., & Kim, H. K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31441-3_16
Kaliuzhnyi, L. V., Rusalovskiy, V. B., Іщенко, А., et al. (2026) · Journal of Telecommunications and Information Technology · doi:10.26636/jtit.2026.3.2637
Multi-Feature Fusion-Based Visual Security Index for Perceptual Image Encryption
Chen, C., Wang, X., & Qu, L. (2026) · Applied Sciences · doi:10.3390/app16188935
Metadata
- Authors
- Rassool, R.
- Affiliations
- RealNetworks (United States) (US)
- Corresponding author
- Rassool, Reza
- Venue
- 2017 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)
- Publisher
- IEEE
- Published
- 2017-06
- Pages
- 1-2
- OpenAlex
- W2737019897
- Cited by
- 235
- References
- 5
- Citations by year
- 2026: 23 · 2025: 39 · 2024: 37 · 2023: 36 · 2022: 30 · 2021: 37 · 2020: 17 · 2019: 12 · 2018: 4
- FWCI
- 2.64
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Physical Sciences › Computer Science › Signal Processing › Video Coding and Compression Technologies
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Keywords
- VMAF, video quality metrics, perceptual video quality, reproducibility, subjective quality assessment, objective quality measurement, 4K video, data rate, quality of experience, subjective-objective correlation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.