AI RESEARCH
SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation
arXiv CS.CV
•
ArXi:2605.29655v1 Announce Type: new Autoregressive multimodal large language models (MLLMs) enable 3D generation but struggle to scale to high-resolution shapes due to inadequate 3D tokenizations. Compact set-based representations discard deterministic spatial ordering, leading to ambiguous sequence prediction, while uniform or octree-based voxel grids preserve ordering at the cost of severe redundancy and excessively long sequences. This structural trade-off limits stable and efficient autoregressive 3D generation.