This is an overview of the available documentation in the VMAF repository.
- FAQ – a collection of frequently asked questions
- Models – a summary of the available pre-trained models
- Features – VMAF's core features (metrics)
- Datasets – an overview of the two publicly available datasets for training custom models
- Confidence Interval – how to use bootstrapping to provide CI estimates for VMAF scores
- Bad Cases – how to report cases of VMAF not working well
- Python library – explains the Python wrapper for VMAF
- ffmpeg – how to use VMAF in conjunction with FFmpeg
- Docker – how to run VMAF with Docker
- External resources – e.g. software using VMAF
- MATLAB – running other quality algorithms (ST-RRED, ST-MAD, SpEED-QA, and BRISQUE) with MATLAB
- Windows – how to build VMAF for Windows
- AOM CTC - how to use VMAF compliant with AOM common test conditions.
- NFLX CTC - how to use NFLX common test conditions.
- Release – how to perform a new release
- References – a list of links and papers