无需法向量即可从点云直接重建显式表面，保留锐利细节。
OffsetOPT: Explicit Surface Reconstruction without Normals
- 用神经网络预测局部几何对应的三角面片
- 通过优化点偏移提升三角预测精度，实现高质量重建
- 适合无法向量或需保留锐利特征的三维重建任务
神经隐式表面重建长期依赖基于等距采样的训练点云和 marching cubes 算法提取显式表面。然而，这些方法通常需要高质量的点法向量才能实现准确重建。本文提出 OffsetOPT，一种直接从 3D 点云重建显式表面的新方法，无需点法向量。该方法包含两个阶段：首先，在均匀分布的训练点云上训练神经网络，预测与局部几何匹配的表面三角形；其次，将训练好的网络冻结，对未见点云通过优化每个点的偏移量，以最大化三角形预测准确性，实现表面重建。相比当前最优方法，OffsetOPT 不仅在整体表面重建上表现更优，还显著保留了尖锐的几何特征。我们在多个基准数据集上验证了其在小尺度物体和大尺度开放曲面上的高精度表现。
原文摘要 · Abstract (English)
Neural surface reconstruction has been dominated by implicit representations with marching cubes for explicit surface extraction. However, those methods typically require high-quality normals for accurate reconstruction. We propose OffsetOPT, a method that reconstructs explicit surfaces directly from 3D point clouds and eliminates the need for point normals. The approach comprises two stages: first, we train a neural network to predict surface triangles based on local point geometry, given uniformly distributed training point clouds. Next, we apply the frozen network to reconstruct surfaces from unseen point clouds by optimizing a per-point offset to maximize the accuracy of triangle predictions. Compared to state-of-the-art methods, OffsetOPT not only excels at reconstructing overall surfaces but also significantly preserves sharp surface features. We demonstrate its accuracy on popular benchmarks, including small-scale shapes and large-scale open surfaces.
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。