PyTorchVideoCompression

Description

PyTorch implementations of learned video compression methods (DVC, FVC, DCVC and related neural codecs) with training and inference code used as a common research baseline.

URL

• Visit resource

Related resources

• AV1 Encoding with libsvtav1 on QencodeThe libsvtav1 encoder (SVT-AV1) is an AV1 implementation tuned for both compression efficiency and parallel performance. This guide covers…
• Open-Source Software Encode/Decode For H.266/VVC ProgressingPhoronix status roundup tracking maturity of the open-source VVC/H.266 ecosystem, including native FFmpeg decoder progress.
• FOSDEM 2024: FFmpeg VVC DecoderFOSDEM Open Media devroom talk on the native in-tree FFmpeg VVC decoder implementation (distinct from wrapping external vvdec).
• 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.
• FOSDEM 2023: VVenC & VVdeC — Open Source Video Encoding and Playback for VVCFOSDEM Open Media devroom talk by Fraunhofer HHI developers presenting the VVenC encoder and VVdeC decoder for the VVC/H.266 codec.
• Differentiable VMAF Re-implementation on PyTorchDifferentiable PyTorch reimplementation of VMAF metric enabling gradient-based codec/RDO optimization, with companion code.
• 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.
• 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.