Adaptive Local Basis Functions for Shape Completion
This addresses the problem of efficient and expressive shape completion for 3D modeling applications, representing an incremental advance over existing methods.
The paper tackles 3D shape completion from partial point clouds by introducing adaptive local basis functions learned end-to-end, resulting in improved performance over state-of-the-art methods in shape completion, detail preservation, generalization, and computational cost.
In this paper, we focus on the task of 3D shape completion from partial point clouds using deep implicit functions. Existing methods seek to use voxelized basis functions or the ones from a certain family of functions (e.g., Gaussians), which leads to high computational costs or limited shape expressivity. On the contrary, our method employs adaptive local basis functions, which are learned end-to-end and not restricted in certain forms. Based on those basis functions, a local-to-local shape completion framework is presented. Our algorithm learns sparse parameterization with a small number of basis functions while preserving local geometric details during completion. Quantitative and qualitative experiments demonstrate that our method outperforms the state-of-the-art methods in shape completion, detail preservation, generalization to unseen geometries, and computational cost. Code and data are at https://github.com/yinghdb/Adaptive-Local-Basis-Functions.