Implicit neural networks have been successfully used for surface reconstruction from point clouds. However, many of them face scalability issues as they encode the isosurface function of a whole object or scene into a single latent vector. To overcome this limitation, a few approaches infer latent vectors on a coarse regular 3D grid or on 3D patches, and interpolate them to answer occupancy queries. In doing so, they loose the direct connection with the input points sampled on the surface of objects, and they attach information uniformly in space rather than where it matters the most, i.e., near the surface. Besides, relying on fixed patch sizes may require discretization tuning. To address these issues, we propose to use point cloud convolutions and compute latent vectors at each input point. We then perform a learning-based interpolation on nearest neighbors using inferred weights. Experiments on both object and scene datasets show that our approach significantly outperforms other methods on most classical metrics, producing finer details and better reconstructing thinner volumes. The code is available at https://github.com/valeoai/POCO.
翻译:从点云层成功地利用隐性内线网络进行表面重建。 但是, 其中许多在将整个对象或场景的等表层功能编码成单一潜质矢量时面临可缩放问题。 为了克服这一限制, 有几个方法在粗糙的正态 3D 网格或3D 补丁网格上推断潜在矢量, 并将这些潜在矢量内插以回答占用询问。 在这样做的时候, 它们松散了与在物体表面取样的输入点的直接连接, 并且在空间而不是最紧要的地方, 即接近表面的地方, 并附上了统一的信息。 此外, 依靠固定的补丁尺寸可能需要进行离散化调整。 为了解决这些问题, 我们提议在每个输入点使用点云变和计算潜值矢量。 然后我们用推断的重量对最近的邻居进行基于学习的内插。 对对象和场景数据集的实验表明, 我们的方法大大优于大多数古典的测量仪的其他方法, 产生更细的细节, 并更好地重建薄度。 代码可在 https://giuthub.com/ valeauaia/ CO. CO 。