A quality heatmap is the picture that answers where: it colors a single frame by local quality, so a blocky sky reads as a hot patch while a clean face stays cool, showing which region failed while the rest held rather than reporting one pooled average. It is possible because some metrics are computed locally before being pooled into a frame score - SSIM is the clearest case, calculated over small overlapping windows whose intermediate values form a quality map you can render over the frame. Reading it is a skill: a dark blob in a detailed region usually means blur or compression noise, while a low-scoring band along the top and bottom edges is often not a quality problem but a letterbox or aspect-ratio mismatch in the setup. The firm rule is that color must never be the only thing carrying meaning - pair the scale with numbers and label the worst region - because a color-only map is unreadable to a colorblind reader or on a grayscale print.

Book cover: Video Streaming, Volume 3 of the Fora Soft Video Engineering HandbookBook cover: Video Encoding, Volume 1 of the Fora Soft Video Engineering HandbookBook cover: AI for Video, Volume 6 of the Fora Soft Video Engineering Handbook

The handbook · 7 volumes

Fora Soft Video Engineering Handbook

A quality heatmap shows where inside the frame quality was lost, which turns a single number into something an encoder engineer can act on. We wrote seven volumes covering the whole video stack, and for heatmaps start with Volume 1: SSIM and VMAF, local quality windows, compression artifacts and rate-quality plots. Written by Nikolay Sapunov, CEO at Fora Soft.

Browse the handbook on Amazon →7 volumes · 9,000+ pages · Kindle & paperback

Know the score dropped but not where in the frame — would a quality heatmap help?

Send us a problem encode with its source: we produce quality heatmaps, point to the regions losing detail and suggest encoder changes. 250+ video products shipped since 2005.

Book a 30-min call →WhatsApp →Email us →