Evaluating Video Quality Metrics for Neural and Traditional Codecs using 4K/UHD-1 Videos
Description
2025 academic benchmark comparing PSNR/SSIM/MS-SSIM/VMAF/LPIPS and no-reference metrics (MUSIQ, FasterVQA, Dover, Q-Align) on modern and AI-based codecs.
Resource details
- Category path
- Media Tools›Quality Analysis & Metrics
- Classification
- Not yet classified
Evaluating Video Quality Metrics for Neural and Traditional Codecs using 4K/UHD-1 Videos is cataloged in Media Tools and Quality Analysis & Metrics.
URL
Related resources
- ic-metricsOptimized C++ implementation of SSIMULACRA2/SSIM/MS-SSIM, roughly 25-30% faster via sub-score pruning.
- VQMTK: Video Quality Metrics ToolkitOpen-source cross-platform tool bundling 14 VQA metrics plus SI/TI spatial/temporal indicators, CLI or Jupyter web UI.
- nr-vqa-consumervideoNo-reference video quality metric tuned for consumer video capture artifacts (sensor noise, motion blur, shake) rather than compression art…
- 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.
- AVT-VQDB-UHD-1-NVCDataset and code for 4K/UHD neural-video-codec quality evaluation, comparing VMAF, AVQBits, FasterVQA, CVQA-FR, LPIPS metrics.
- 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.
- VMAF-torchPyTorch reimplementation of VMAF metric, GPU/gradient-friendly for use in learned codec optimization loops.
- aws-batch-with-FFmpegReference architecture running FFmpeg containers (ARM64/x86-64/NVIDIA/Xilinx) on AWS Batch with Spot compute environments and SDK/REST job…
- Bitrate Ladder Construction via Transfer Learning and Spatio-Temporal FeaturesML-based bitrate ladder optimization achieving 94.1% complexity reduction at only 1.71% BD-rate cost using transfer learning.