Differentiable VMAF Re-implementation on PyTorch
Differentiable PyTorch reimplementation of VMAF metric enabling gradient-based codec/RDO optimization, with companion code.
Link
Related resources
- Applying Objective Quality Metrics to Video-Codec ComparisonStudy of 789 encoded streams and 320k subjective scores analyzing VMAF correlation per colorspace for codec comparison.
- Are We Compressed YetDistributed encode/decode + BD-rate + VMAF benchmarking harness originally for Daala, adopted by AOM community for comparative testing of A…
- Benchmarking Conventional and Learned Video Codecs with a Low-Delay ConfigurationAcademic benchmark comparing traditional (HEVC/VVC) and learned video codecs under low-delay configuration constraints.
- OpenDCVCs: Reproducible PyTorch Reimplementation of the DCVC Codec SeriesIndependent open reimplementation with training+eval code of the whole Microsoft DCVC learned video codec family (prior official releases w…
- Cool-chic: Coordinate-based Low Complexity Hierarchical Image/Video CodecUltra-low-complexity overfitted/coordinate-based learned video codec using ~800 parameters, with companion open-source implementation.
- Opus (xiph/opus)Reference implementation of the Opus audio codec, recently adding deep-learning-based packet loss concealment.
- Performance Comparison of AV1, JEM, VP9, and HEVC EncodersFraunhofer HHI SPIE 2017 paper comparing codec internals, BD-BR, and complexity across AV1, JEM, VP9, and HEVC.
- nano-hevcMinimal educational HEVC encoder written in pure Python, readable-over-fast, for teaching codec internals.
- FOSDEM 2024: VVdeC<>Arm — Optimizing an Open Source VVC Decoder for Arm ArchitecturesFOSDEM Open Media devroom talk detailing Arm-specific performance optimization work on the open-source VVdeC VVC decoder.
- jxs (JPEG XS reference)Reference software implementation of ISO/IEC 21122-5 (JPEG XS) including jxs_encoder binary, supports PNM/PGX/raw YUV/RGB input.