LoG3D：通过局部到全局分块实现超高分辨率三维形状建模
LoG3D: Ultra-High-Resolution 3D Shape Modeling via Local-to-Global Partitioning
把 UDF 体数据切成均匀子块（UBlocks），用 3D 卷积抓局部细节、稀疏 Transformer 建全局一致性，再配合 Pad-Average 消除块边界接缝——这套局部到全局的分块策略可直接迁移到高分辨率 NeRF/高斯泼溅体素表示或任意大尺度隐式场的建模与生成。
原文依据 a local-to-global (LoG) architecture that processes the UDF by partitioning it into uniform subvolumes, termed UBlocks
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论生成高保真三维内容仍是一项根本性挑战，原因在于既要表示任意拓扑（如开放曲面与复杂的内部结构），又要保留几何细节。当前主流的基于有符号距离场（SDF）的方法受制于代价高昂的水密预处理，且难以处理非流形几何；而点云表示则常常出现采样伪影与表面不连续。为克服这些局限，我们提出了一种基于无符号距离场（UDF）的新型三维变分自编码器（VAE）框架——UDF 是一种更鲁棒、计算更高效的表示，能够自然处理复杂且不完整的形状。我们的核心创新是一种局部到全局（LoG）架构，它通过将 UDF 划分为均匀子体块（称为 UBlocks）来处理该表示。该架构将用于捕捉局部细节的三维卷积与用于施加全局一致性的稀疏 Transformer 相结合。一种 Pad-Average 策略进一步确保重建过程中子体块边界处的平滑过渡。这种模块化设计使其能够无缝扩展至高达 2048^3 的超高分辨率——这是此前三维 VAE 无法达到的水平。实验表明，该方法在重建精度与生成质量上均达到最优性能，并带来更优的表面平滑度与几何灵活性。
英文原文摘要 1397 字符
Generating high-fidelity 3D contents remains a fundamental challenge due to the complexity of representing arbitrary topologies--such as open surfaces and intricate internal structures--while preserving geometric details. Prevailing methods based on signed distance fields (SDFs) are hampered by costly watertight preprocessing and struggle with non-manifold geometries, while point-cloud representations often suffer from sampling artifacts and surface discontinuities. To overcome these limitations, we propose a novel 3D variational autoencoder (VAE) framework built upon unsigned distance fields (UDFs)--a more robust and computationally efficient representation that naturally handles complex and incomplete shapes. Our core innovation is a local-to-global (LoG) architecture that processes the UDF by partitioning it into uniform subvolumes, termed UBlocks. This architecture couples 3D convolutions for capturing local detail with sparse transformers for enforcing global coherence. A Pad-Average strategy further ensures smooth transitions at subvolume boundaries during reconstruction. This modular design enables seamless scaling to ultra-high resolutions up to 2048^3-a regime previously unattainable for 3D VAEs. Experiments demonstrate state-of-the-art performance in both reconstruction accuracy and generative quality, yielding superior surface smoothness and geometric flexibility.