turbo-metrics
CUDA GPU-accelerated video quality metrics: XPSNR, Butteraugli, VMAF, and CAMBI banding detection.
Link
Related resources
- Vship — GPU visual fidelity metricsGPU-accelerated (HIP/CUDA) implementation of visual quality metrics SSIMULACRA2, Butteraugli and ColorVideoVDP for fast perceptual video co…
- psy-ex/metricsPerceptual video metrics toolkit computing SSIMULACRA2, Butteraugli, CVVDP, weighted XPSNR, VMAF NEG, SSIM, and PSNR via helper scripts.
- FFMetricsWindows GUI that visualizes PSNR, SSIM, XPSNR, and VMAF computed via FFmpeg with interactive graphs and batch processing.
- ssimulacra2_rsRust implementation of the SSIMULACRA2 perceptual quality metric, among the first with video input support.
- sxpsnrStandalone XPSNR CLI computing the perceptually-weighted PSNR metric between two YUV/Y4M sources.
- butteraugli (Rust port)Pure Rust port of Butteraugli from libjxl with XYB color, visual masking, and multi-scale bands, validated to within 0.001% of the referenc…
- SimpleVQADeep-learning no-reference video quality assessment for user-generated content, in PyTorch with SlowFast feature extraction.
- AutoShotCVPR-NAS 2023 shot boundary detection model with a NAS-optimized architecture and the new SHOT dataset (853 videos, 11,606 annotations).
- AutoSubSyncSubtitle auto-sync GUI wrapping ffsubsync/autosubsync/alass; can sync against a reference subtitle instead of the video.
- SceneSeg (Local-to-Global Scene Segmentation)CVPR 2020 multimodal movie scene segmentation using place and audio features on the MovieNet dataset; reference ML baseline with code.