CompressAI-Vision: Video Compression for Machines Benchmark
Paper + framework for designing, testing and comparing "video coding for machines" pipelines, mixing neural CompressAI models against VVC/H.266 for machine-vision tasks.
Link
Related resources
- MLVC: Multi-platform Learned Video Codec for Real-World DeploymentAcademic paper on a neural video codec targeting competitive compression, real-time speed, and cross-platform (Apple/Intel/Qualcomm NPU) in…
- Compression efficiency analysis of AV1, VVC, and HEVC for random access applicationsAPSIPA Transactions paper quantifying bitrate savings and encode/decode runtime ratios of AV1 vs VTM vs HM for random-access use cases.
- Comparing VVC, HEVC and AV1 using Objective and Subjective AssessmentsBristol Vision Institute study comparing VVC, HEVC, AV1 with both objective metrics (PSNR/VMAF) and subjective assessment data.
- A Comprehensive Review of Software and Hardware Energy Efficiency of Video DecodersCross-codec (AV1/HEVC/VVC/AVM/VP9) energy efficiency and compression review across software and hardware decoders.
- Comparative Evaluation of VVC, HEVC, H.264, AV1, and VP9 Encoders for Low-Delay Video ApplicationsIEEE paper benchmarking five codec encoders (VVC, HEVC, H.264, AV1, VP9) specifically for low-delay video applications.
- 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.
- Differentiable VMAF Re-implementation on PyTorchDifferentiable PyTorch reimplementation of VMAF metric enabling gradient-based codec/RDO optimization, with companion code.
- nano-hevcMinimal educational HEVC encoder written in pure Python, readable-over-fast, for teaching codec internals.
- Opus (xiph/opus)Reference implementation of the Opus audio codec, recently adding deep-learning-based packet loss concealment.
- dav1d.wasmWASM port of the dav1d AV1 decoder, SIMD-optimized with TypeScript interfaces, aimed at production use in browsers.