r10

• CAMBI: Add max_log_contrast parameter.
• Add Metric function.

r9

• model parameter no longer defaults to 0 so feature metrics can be calculated alone.
• Add CAMBI filter.
• Add vsvmafxml.

r8

• Migrate to VS API4.

r7

• Upgrade to libvmaf v2 API and revise the parameters accordingly. The model files are now built-in in the library and hence you can delete the entire model folder if you have previous versions installed.
• Add vmaf_v0.6.1neg model.
• Add PSNR-HVS and CIEDE2000 metrics.

r6

• Update to libvmaf 1.3.15.
• Add csv log format.
• Minor optimization.

r5

• Accept clips of any planar format with integer sample type of 8-16 bit depth, except RGB. Note that libvmaf only uses luma plane for calculating scores.
• Remove parameter psnr.

r4

• Update libvmaf to v1.3.14, which reports aggregate CI scores and fix empty model name in log.

r3

• Update libvmaf to v1.3.13, which includes performance improvement.
• Change default pool to 1.
• Set libvmaf's threads according to core's number of worker threads.

r2.1

• Replace Autotools with Meson build system.

r2

• Scale 10-bit pixel values to 8-bit range for correct score calculation.
• Use stricter linear frame request since VMAF score will change if frame order is different.
• Report aggregate PSNR, SSIM, and MS-SSIM scores in addition to VMAF score.