Get the latest tech news
Video encoding requires using your eyes
HAAAAAAANK LOOK AT THE FUCKING IMAGE WHEN ENCODING VIDEO HAAAAAAAAAAAAAAAAAAAANK
Netflix’s catalog is pretty broad, and video encoding has seen numerous attempts at content-based specialization that turned out to be worse than focusing on improving things generically and adding tuning knobs. I was curious how they’d solve the lack of a reference when training a downscaling model, and this sort of explains it; they optimized for PSNR when upscaled back to the original resolution, post-downscaling. Through our experimentation, involving objective measurements and subjective visual tests, we found that the deep downscaler improves quality across various conventional video codecs and encoding configurations.
Or read this on Hacker News