A dependency-light Python script (standard library only) that reads a libvmaf JSON log holding both the default and NEG VMAF scores (or two separate logs), reports each score pooled four ways (mean, harmonic mean, 5th percentile, single worst frame), computes the per-frame and overall enhancement-gain gap (default minus NEG), flags any clip whose gap is large enough that the default score is riding on enhancement rather than compression, and warns on any frame scoring above 100. Includes the cur
Download free PDF
The handbook · 7 volumes
Fora Soft Video Engineering Handbook
This checker compares default and NEG VMAF, pools both four ways and flags clips whose score rides on enhancement such as sharpening rather than compression. Our seven-volume handbook goes deeper: Volume 1 on VMAF variants and quality metrics, Volume 3 on ladders and QoE, and Volume 6 on AI enhancement. Written by Nikolay Sapunov, CEO at Fora Soft.
Suspect your VMAF scores are inflated by sharpening or enhancement?
Send us your encodes and VMAF logs: we will check the default-versus-NEG gap and tell you which quality gains are real. 250+ video products shipped since 2005.
You get a realistic estimate, technical recommendations and next steps. Free, no obligations.
