Netflix vmaf: Perceptual video quality assessment based on multi-method fusion

Netflix's VMAF is an Emmy-winning perceptual video quality assessment algorithm that measures video quality by fusing multiple evaluation methods. The software package includes a C library (libvmaf) and Python tools for training custom quality models, along with implementations of other metrics like PSNR, SSIM, and MS-SSIM. Netflix recently released VMAF v1 models with improvements and optimizations, while also open-sourcing CAMBI, a detector for banding artifacts in videos.