AI RESEARCH

Beyond Spatial Compression: Interface-Centric Generative States for Open-World 3D Structure

arXiv CS.LG

ArXi:2605.10438v1 Announce Type: new Current 3D tokenizers largely treat representation as spatial compression: compact codes reconstruct surface geometry, but leave component ownership and attachment validity implicit. In open-world assets with intersecting components, noisy topology, and weak canonical structure, this creates a representation mismatch: local shape, component identity, and assembly relations become entangled in a latent stream and are not natively addressable during decoding.