BuildAnyPoint：从多样点云中抽象结构化三维建筑
BuildAnyPoint: 3D Building Structured Abstraction from Diverse Point Clouds
把「点云分布恢复」当作条件潜扩散任务、再用 decoder-only Transformer 自回归生成紧凑网格的两阶段级联思路，可直接迁移到稀疏/噪声点云驱动的结构化三维生成与补全；其恢复出的点云还能作为点云补全的中间表示来提升表面精度与分布均匀性。
原文依据 we design a Loosely Cascaded Diffusion Transformer (Loca-DiT) that initially recovers the underlying distribution from noisy or sparse points
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 BuildAnyPoint，一个用于从分布多样的点云（例如机载激光雷达与运动恢复结构所采集的点云）中进行结构化三维建筑重建的新型生成式框架。为在这种高度欠约束的设定下恢复艺术家创作的建筑抽象表示，我们利用显式三维生成先验在自回归网格生成中的作用。具体而言，我们设计了一个松散级联扩散 Transformer（Loca-DiT），它首先从含噪或稀疏的点中恢复底层分布，随后自回归地将其封装为紧凑网格。我们首先将分布恢复表述为条件生成任务，通过训练以输入点云为条件的潜变量扩散模型来实现；然后基于恢复出的点云，定制一个仅解码器 Transformer 用于条件自回归网格生成。相比先前的建筑抽象方法，我们的方法在定性与定量上均取得显著提升。此外，该方法恢复出的点云在建筑点云补全基准上表现强劲，展现出更高的表面精度与分布均匀性，进一步印证了其有效性。
英文原文摘要 1235 字符
We introduce BuildAnyPoint, a novel generative framework for structured 3D building reconstruction from point clouds with diverse distributions, such as those captured by airborne LiDAR and Structure-from-Motion.To recover artist-created building abstraction in this highly underconstrained setting, we capitalize on the role of explicit 3D generative priors in autoregressive mesh generation.Specifically, we design a Loosely Cascaded Diffusion Transformer (Loca-DiT) that initially recovers the underlying distribution from noisy or sparse points, followed by autoregressively encapsulating them into compact meshes.We first formulate distribution recovery as a conditional generation task by training latent diffusion models conditioned on input point clouds, and then tailor a decoder-only transformer for conditional autoregressive mesh generation based on the recovered point clouds.Our method delivers substantial qualitative and quantitative improvements over prior building abstraction methods. Furthermore, the effectiveness of our approach is evidenced by the strong performance of its recovered point clouds on building point cloud completion benchmarks, which exhibit improved surface accuracy and distribution uniformity.