A Low-Complexity Perceptual Video Quality Metric for SVT-AV1

Mile-High Video Conference 2025 paper on encoder-integrated low-complexity perceptual quality metric for SVT-AV1.

Link

Related resources

  • VFIPSPerceptual quality metric specifically for video frame interpolation artifacts, PyTorch implementation.
  • Q-Bench-VideoCVPR 2025 benchmark for LMM video quality understanding across technical/aesthetic/temporal/AIGC axes.
  • T2VQAACM MM'24 text-to-video quality assessment model using LLM-based scoring.
  • bitstream_mode3_videoparserOpen-source parser tied to ITU-T P.1204.3 QoE model, academic VP9-capable feature extractor from QoEX 2020 paper.
  • BVQA_BenchmarkBlind (no-reference) VQA benchmarking toolkit comparing multiple models.
  • CompressedVQA-AEVFull-reference + no-reference VQA for asymmetric-encoded video, QoMEX 2026 challenge solution using SigLIP2+Swin-B.
  • CAMP-VQAWACV 2026 caption-embedded multimodal no-reference VQA model for compressed video, with code and HF demo.
  • PXNR No-Reference Video Quality EstimationEricsson's sample implementation of the ITU-T P.NATS phase 2 no-reference video quality estimation module.
  • fssimu2Zig implementation of SSIMULACRA2 metric, ~23% faster and ~40% less memory than the reference implementation.
  • ffmpeg-queueFastify + Redis job queue for dispatching FFmpeg transcoding jobs, Docker Compose ready, production-used.