Generative Vision Atlas

Representation option

Hybrid semantic + detail codebook

Two coupled codebooks/branches: one capturing semantic content, one capturing pixel-level detail, kept aligned so both understanding and generation/reconstruction stay strong.

Introduced by

Used by (4)

DecQ, FlatDINO, LV-RAE, TokenFlow

Alternatives on this axis

Continuous tokens, Deep-compression latent, Frozen encoder + trained decoder, Multi-scale (next-scale) tokens, Pixels, Semantic / foundation latent, VAE latent

← All Representation options