Encoding 3D points is one of the primary steps in learning-based implicit scene representation. Using features that gather information from neighbors with multi-resolution grids has proven to be the best geometric encoder for this task. However, prior techniques do not exploit some characteristics of most objects or scenes, such as surface normals and local smoothness. This paper is the first to exploit those 3D characteristics in 3D geometric encoders explicitly. In contrast to prior work on using multiple levels of details, regular cube grids, and trilinear interpolation, we propose 3D-oriented grids with a novel cylindrical volumetric interpolation for modeling local planar invariance. In addition, we explicitly include a local feature aggregation for feature regularization and smoothing of the cylindrical interpolation features. We evaluate our approach on ABC, Thingi10k, ShapeNet, and Matterport3D, for object and scene representation. Compared to the use of regular grids, our geometric encoder is shown to converge in fewer steps and obtain sharper 3D surfaces. When compared to the prior techniques, our method gets state-of-the-art results.

翻译：编码三维点是基于学习的隐式场景表示中的关键步骤之一。利用多分辨率网格从邻域收集信息的特征已被证明是此任务的最佳几何编码器。然而，现有技术未能充分利用大多数物体或场景的特性，例如表面法线和局部平滑性。本文首次在三维几何编码器中显式利用这些三维特征。与先前利用多层级细节、规则立方体网格和三线性插值的工作不同，我们提出三维面向网格，并结合一种新颖的圆柱形体积插值方法以建模局部平面不变性。此外，我们显式引入局部特征聚合机制，用于对圆柱插值特征进行正则化与平滑处理。我们在ABC、Thingi10k、ShapeNet和Matterport3D数据集上评估了该方法在物体与场景表示中的表现。与使用规则网格相比，我们的几何编码器在更少迭代步数内收敛，并能够重建更锐利的三维表面。与现有技术相比，本方法取得了最优结果。