Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

Triplane-based multi-camera tokenization

Tokenizes multi-camera input using a triplane-based representation.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See multimodal architecture for the methods filed beside it.

Also called triplane-based multi-camera tokenizer.

Filed under model architecture › multimodal architecture