学习镶嵌：通过递归谱划分生成点云
Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning
浏览论文内容
中文总结 AI 辅助
该研究提出自回归框架PointRSP，通过拓扑保留的递归谱划分实现点云生成，引入拓扑感知划分自编码器与双流级联生成器，在生成质量、多样性及复杂3D拓扑泛化上达最优性能。
中文摘要 AI 辅助
自回归模型已成为点云生成的有效范式。然而，大多数现有方法依赖启发式分词策略，如空间排序或随机下采样，这些策略常破坏点云固有拓扑，削弱生成形状的结构连贯性。本文提出PointRSP，一种自回归框架，将点云生成重新表述为通过递归谱划分实现拓扑保留的镶嵌过程。我们引入拓扑感知划分自编码器，而非启发式构建令牌序列，通过混合递归谱划分策略将非结构化点云分解为非平衡二叉树。该层次表示提供确定性几何蓝图，在量化潜空间中保留拓扑关系的同时捕获多尺度结构依赖。为在该空间合成形状，我们提出双流级联生成器，联合建模结构演化与特征合成。此外，我们设计几何校准位置编码机制，利用多尺度结构中心锚定潜嵌入，在结构形成早期稳定级联生成。大量实验表明，PointRSP在生成质量与多样性上达到当前最优性能，展现出对复杂3D拓扑的强泛化能力。
英文摘要
Autoregressive models have emerged as an effective paradigm for point cloud generation. However, most existing approaches rely on heuristic tokenization strategies, such as spatial sorting or stochastic downsampling, which often disrupt intrinsic point cloud topology and weaken the structural coherence of the generated shapes. In this paper, we present PointRSP, an autoregressive framework that reformulates point cloud generation as a topology-preserving tessellation process via recursive spectral partitioning. Instead of constructing token sequences heuristically, we introduce a topology-aware partitioning autoencoder that decomposes an unstructured point cloud into a non-balanced binary tree through a hybrid recursive spectral partitioning strategy. This hierarchical representation provides a deterministic geometric blueprint that preserves topological relationships while capturing multiscale structural dependencies within a quantized latent space. To synthesize shapes in this space, we propose a dual-stream cascaded generator that jointly models structural evolution and feature synthesis. In addition, we design a geometry-calibrated positional encoding mechanism that anchors latent embeddings using multi-scale structural centers, which stabilizes cascaded generation during the early stages of structural formation. Extensive experiments show that PointRSP achieves state-of-the-art performance in generation quality and diversity, demonstrating strong generalization across complex 3D topologies.
发表机构
- South China University of Technology（华南理工大学）
- University of Chinese Academy of Sciences（中国科学院大学）
- City University of Hong Kong（香港城市大学）
- Singapore Management University（新加坡管理大学）
机构由 AI 辅助整理，请以论文原文为准。
