Fig.1

Concept

Gated spatial consistency

Gated spatial consistency measures whether a world model redraws a scene region the same way when the camera revisits it, but only over the pixels where a comparison is actually valid. The "gated" part is the key: instead of diffing two whole frames, you first compute a mask…

The rest of “Gated spatial consistency” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.

Log in to unlock

← Back to the library

Gated spatial consistency, explained · Fig. 1