Diffusion models’ role in image compression
A coauthor says the article reviews generative compression and “near-optimal” tradeoffs between data rate, image distortion and realism.
TLDR
Diffusion models can do more than generate images: they can save us from transmitting all their detail, according to a coauthor of an IEEE BITS article. The coauthor describes the review as covering generative compression and near-optimal tradeoffs among how much data is sent, image distortion and realism, and credits Yibo Yang with leading the work.
Combined views
—
1 Source, first seen ago
