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
- TokenFlow 2024-12
Alternatives on this axis
Continuous tokens, Deep-compression latent, Frozen encoder + trained decoder, Multi-scale (next-scale) tokens, Pixels, Semantic / foundation latent, VAE latent