SVT-AV1-PSY — psychovisual SVT-AV1 fork

Community fork of SVT-AV1 adding psychovisual fidelity enhancements (perceptual tuning, metrics) that are being upstreamed to the mainline encoder.

Link

• Visit resource

Related resources

• av1-grainRust library for parsing and generating AV1 film grain synthesis data, extracted from the rav1e encoder.
• rAV1atorGUI application for rav1e video encoding paired with Opus audio encoding.
• NotEnoughAV1Encodes-QtLinux Qt GUI wrapping aomenc/rav1e/SVT-AV1 encoders with chunked parallel encoding support.
• Comparing H.265/HEVC and VP9: Impact of High Frame Rates on Perceptual QualityAcademic comparison of HEVC and VP9 codecs under high frame-rate conditions, including ffmpeg/libvpx tuning parameters used.
• hardware-video-encoderHardware encode wrapper (VAAPI/NVENC) for H.264/HEVC via FFmpeg libraries, supporting VBR/CQP on Linux.
• 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.
• 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.
• Differentiable VMAF Re-implementation on PyTorchDifferentiable PyTorch reimplementation of VMAF metric enabling gradient-based codec/RDO optimization, with companion code.