causal

Video compression targets human perception not data fidelity

Unlike lossless ZIP compression, video and audio codecs degrade the signal by 100x-1000x by exploiting how human perception works (e.g., moving from RGB to YUV and downscaling color resolution because the eye is less sensitive to color than brightness), so the goal is to maximize perceived quality, not preserve the original bits.

causalpending

Speaker

Jean-Baptiste Kempf

Evidence Quote

“So all the codecs, either for audio, mimic basically how your ear works... and same for your eyes”

Source

Lex Fridman Podcast #496 - FFmpeg— Lex Fridman Podcast
Created: 6/13/2026, 12:26:55 AM

Your notes

Loading notes...