vhh-sbd

PyTorch shot boundary detector from AIT's Visual History of the Holocaust project, focused on abrupt transitions in archival footage.

Link

Related resources

  • shot-boundary-detectionSurvey and implementations of multiple shot-boundary detection techniques including hard-cuts, fades, and neural-net methods.
  • BFI DataDigipres Transcoding ScriptsArchival-grade cron-driven batch transcode scripts used by the BFI National Archive, focused on FFV1/V210 preservation workflows.
  • Vship (Vapoursynth-HIP-SSIMU2)GPU-accelerated (HIP/CUDA) visual fidelity metrics library implementing SSIMULACRA2, Butteraugli, and CVVDP.
  • ButteraugliGoogle's psychovisual difference metric library for images/video frames, outputs scalar score plus visual diff map.
  • VFIPSPerceptual quality metric specifically for video frame interpolation artifacts, PyTorch implementation.
  • ffmpeg-queueFastify + Redis job queue for dispatching FFmpeg transcoding jobs, Docker Compose ready, production-used.
  • 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.
  • 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.