用自适应分块方式生成3D形状，让模型更快更准。
SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation
- 根据形状复杂度动态划分超体素，保持空间顺序
- 序列长度仅为均匀体素的12.8%，生成质量领先
- 适合需要高效高精度3D生成的研究与应用
自回归多模态大语言模型虽能生成3D形状，但受限于低效的3D标记化方法。传统集合表示丢失空间顺序，导致预测模糊；而均匀或八叉树体素网格虽保留顺序，却存在严重冗余和过长序列。本文提出SuperVoxelGPT，一种以表征为核心的框架，通过自适应且确定性排序的超体素标记化解决该矛盾。给定提示后，先预测粗粒度几何显著性分布，再基于显著性引导的重心维诺细分构建形状自适应的超体素分割，将细粒度单元分配至复杂区域，平滑区域使用更大单元。在此有序布局下，引入SuperVoxelVAE并微调预训练MLLM，实现自回归生成超体素标记。在Trellis-500K数据集上的实验表明，SuperVoxelGPT将序列长度降至均匀体素的12.8%，达到当前最佳生成质量，并相较先前方法平均提速10倍。
原文摘要 · Abstract (English)
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. We present SuperVoxelGPT, a representation-first framework that resolves this tension through adaptive and deterministically ordered supervoxel tokenization. Given a prompt, we first predict a coarse geometric saliency distribution and construct a shape-adaptive supervoxel partition using saliency-guided centroidal Voronoi tessellation, allocating fine-grained cells to complex regions and larger cells to smooth regions. Conditioned on this prompt and ordered supervoxel layout, we introduce a SuperVoxelVAE and fine-tune a pretrained MLLM to autoregressively generate supervoxel tokens. Experiments using Trellis-500K data show that SuperVoxelGPT reduces token sequence length to 12.8% of uniform voxel tokenization while achieving state-of-the-art generation quality and an average 10x speedup over prior methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。