Skip to main content

Adaptive multi‑stage video quality audit pipeline

Project description

🎬 CineInfini – Video Quality Auditor

License: MIT Python 3.9+ Code style: black

CineInfini is an open‑source, modular pipeline for automatic, explainable video quality auditing. It goes beyond traditional fidelity metrics (PSNR, SSIM) by assessing temporal stability, identity consistency, semantic coherence, and narrative flow – all in a single GPU‑accelerated pipeline.

FeaturesInstallationQuick StartDocumentationContributing


✨ Features

  • Adaptive shot detection – HSV histogram with percentile‑based threshold
  • 7 intra‑shot metrics – motion peak (optical flow), 3D‑SSIM, flicker, identity drift (ArcFace), long‑range SSIM, high‑frequency flicker, CLIP temporal consistency
  • Inter‑shot coherence – structure (SSIM), style (histogram), semantic (CLIP)
  • Narrative coherence – DINOv2 cosine similarity between shots
  • Two‑stage audit – automatically optimises processing parameters and composite weights
  • GPU acceleration – CUDA for CLIP/DINOv2, parallel shot processing (4 workers)
  • Exhaustive reports – Markdown dashboards with bar charts, radar plots, improvement suggestions, and JSON exports
  • Benchmark mode – compare multiple videos (synthetic / real) with inter‑video dashboards

🛠 Installation

From PyPI (recommended)

pip install cineinfini-audit

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cineinfini_audit-0.1.2.tar.gz (25.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

cineinfini_audit-0.1.2-py3-none-any.whl (25.9 kB view details)

Uploaded Python 3

File details

Details for the file cineinfini_audit-0.1.2.tar.gz.

File metadata

  • Download URL: cineinfini_audit-0.1.2.tar.gz
  • Upload date:
  • Size: 25.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for cineinfini_audit-0.1.2.tar.gz
Algorithm Hash digest
SHA256 4ac6fd7933b72d7638e521c3622a7cb50ab51152e78fd3314931f9e512073c3b
MD5 4619f256c8ff0d5e15fab663eaacff65
BLAKE2b-256 120ba9de021478835a503b64b7bf2b28ef8d424f681d6cb1b0f20077e6441017

See more details on using hashes here.

Provenance

The following attestation bundles were made for cineinfini_audit-0.1.2.tar.gz:

Publisher: publish.yml on CineInfini/Video_Quality_Auditor

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file cineinfini_audit-0.1.2-py3-none-any.whl.

File metadata

File hashes

Hashes for cineinfini_audit-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 942357f181e6c78c6feefccd0e6d906281458df2b5c7cb8493cdde3d68b207d9
MD5 8d44ef827285c966e0d7d548606756ba
BLAKE2b-256 d7606423258803a7f3ff6a88d9734139b2a2dc2f584d29112bf6c3191de1cd7a

See more details on using hashes here.

Provenance

The following attestation bundles were made for cineinfini_audit-0.1.2-py3-none-any.whl:

Publisher: publish.yml on CineInfini/Video_Quality_Auditor

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page