Toward a Better Quality Metric for the Video Community

Netflix Tech Blog article discussing the need for improved video quality metrics beyond existing ones like PSNR or SSIM, and how metrics like VMAF were developed to better reflect human perception.

Link

• Visit resource

Related resources

• videojs-vastVideo.js plugin for VAST/VMAP ad playback, wrapping vast-client-js for player integration.
• vast-playerBrowser VAST linear-creative ad playback library: ad tag requests, wrapper resolution, MediaFile selection, VPAID init, and tracking pixels.
• vast-vmapJavaScript library parsing IAB VAST 2.0/3.0 and VMAP 1.0 ad schemas with explicit tracking model (caller invokes track() rather than DOM wa…
• Google IMA/DAI HTML5 SDK SamplesOfficial Google samples for client-side (IMA) pre-roll ad insertion and server-side/SGAI dynamic ad insertion streams stitched with HLS.js.
• vast-2-sgaiConverts VAST XML ad responses into HLS interstitial AssetLists and DASH Alternative MPDs for Server-Guided Ad Insertion (SGAI).
• Evaluating Video Quality Metrics for Neural and Traditional Codecs (4K/UHD-1)Academic comparison of VMAF, AVQBits, and FasterVQA no-reference quality metrics on 4K content.
• VMAF-torchPyTorch reimplementation of VMAF metric, GPU/gradient-friendly for use in learned codec optimization loops.
• nr-vqa-consumervideoNo-reference video quality metric tuned for consumer video capture artifacts (sensor noise, motion blur, shake) rather than compression art…
• CompressedVQA: Full/No-Reference VQA for Compressed UGC VideoICME 2021 grand challenge-winning full-reference and no-reference video quality models for compressed user-generated content.
• 2BiVQA: Double Bi-LSTM No-Reference Video Quality AssessmentNo-reference VQA model for UGC video using double Bi-LSTM, companion code to arXiv:2208.14774.