论文标题
Points2surf：从点云补丁学习隐式表面
Points2Surf: Learning Implicit Surfaces from Point Cloud Patches
论文作者
论文摘要
任何基于扫描的资产创建工作流程中的关键步骤是将无序点云转换为表面。经典方法（例如，泊松重建）在存在嘈杂和部分扫描的情况下开始降解。因此，最近提出了基于深度学习的方法，即使是通过部分扫描，也可以产生完整的表面。但是，这种数据驱动的方法努力将具有较大几何和拓扑变化的新形状概括为概括。我们提出了Points2Surf，这是一个基于补丁的新型学习框架，可直接从无需正常的原始扫描中产生准确的表面。在详细的本地补丁和粗略的全球信息的结合下，学习先前的学习，可以提高概括性能和重建精度。我们对合成数据和真实数据的广泛比较表明，我们的方法比以前看不见的类别的最先进的替代方案具有明显的优势（平均而言，Points2Surf将重建误差降低了30％，而SPR比SPR的重建误差降低了30％，而基于深度学习的SOTA方法则在某些情况下以较长的计算时间和较小的计算时间增加了基于深度学习的SOTA方法）。我们的源代码，预培训模型和数据集可在以下网址提供：https：//github.com/erlerphilipp/points2surf
A key step in any scanning-based asset creation workflow is to convert unordered point clouds to a surface. Classical methods (e.g., Poisson reconstruction) start to degrade in the presence of noisy and partial scans. Hence, deep learning based methods have recently been proposed to produce complete surfaces, even from partial scans. However, such data-driven methods struggle to generalize to new shapes with large geometric and topological variations. We present Points2Surf, a novel patch-based learning framework that produces accurate surfaces directly from raw scans without normals. Learning a prior over a combination of detailed local patches and coarse global information improves generalization performance and reconstruction accuracy. Our extensive comparison on both synthetic and real data demonstrates a clear advantage of our method over state-of-the-art alternatives on previously unseen classes (on average, Points2Surf brings down reconstruction error by 30% over SPR and by 270%+ over deep learning based SotA methods) at the cost of longer computation times and a slight increase in small-scale topological noise in some cases. Our source code, pre-trained model, and dataset are available on: https://github.com/ErlerPhilipp/points2surf
