Limin Jiang

Rethinking Serialization in Linear 3D Vision: Decoupling Anisotropic Geometry from Isotropic Semantics

Current linear State-Space Models for 3D point clouds typically rely on 1D serialization (e.g., Hilbert curves) for global modeling. Such rigid ordering disrupts spatial continuity in dense scenes, introducing what we term Serialization Bias. We propose AnIsoNet, a framework that decouples anisotrop…