Shape Generation using Spatially Partitioned Point Clouds
This addresses the problem of efficient and high-quality 3D shape generation for computer graphics and vision applications, offering incremental improvements over existing methods.
The paper tackles 3D shape generation by proposing a method that uses spatially partitioned point clouds with kd-trees and PCA, then learns a distribution over shape coefficients using a generative-adversarial framework, resulting in a lightweight and scalable approach that outperforms simpler linear models on ShapeNet categories.
We propose a method to generate 3D shapes using point clouds. Given a point-cloud representation of a 3D shape, our method builds a kd-tree to spatially partition the points. This orders them consistently across all shapes, resulting in reasonably good correspondences across all shapes. We then use PCA analysis to derive a linear shape basis across the spatially partitioned points, and optimize the point ordering by iteratively minimizing the PCA reconstruction error. Even with the spatial sorting, the point clouds are inherently noisy and the resulting distribution over the shape coefficients can be highly multi-modal. We propose to use the expressive power of neural networks to learn a distribution over the shape coefficients in a generative-adversarial framework. Compared to 3D shape generative models trained on voxel-representations, our point-based method is considerably more light-weight and scalable, with little loss of quality. It also outperforms simpler linear factor models such as Probabilistic PCA, both qualitatively and quantitatively, on a number of categories from the ShapeNet dataset. Furthermore, our method can easily incorporate other point attributes such as normal and color information, an additional advantage over voxel-based representations.