Writing Geometry into the Generative State: GAE Unifies Perception and Generation with a Geometry-Native Latent Space
The work introduces the geometry-native autoencoder (GAE), which compresses the four feature levels of the frozen geometry foundation model DA3 into a single compact latent of 64 or 128 channels that decodes jointly to RGB, depth, cameras, and point maps, and in controlled comparisons holding the generator and training protocol fixed it lowers FVD on RealEstate10K and DL3DV and roughly halves camera-trajectory error on RealEstate10K relative to the strongest non-GAE latent.