PointInverter: Point Cloud Reconstruction and Editing via a Generative Model with Shape Priors

作者：Jaeyeon Kim, Binh-Son Hua, D. Nguyen, Sai-Kit Yeung · 发表于：IEEE Workshop/Winter Conference on Applications of Computer Vision · 年份：2022 · DOI：10.1109/wacv56688.2023.00066 · 被引用次数：10 · 研究领域：Computer Science

In this paper, we propose a new method for mapping a 3D point cloud to the latent space of a 3D generative adversarial network. Our generative model for 3D point clouds is based on SP-GAN, a state-of-the-art sphere-guided 3D point cloud generator. We derive an efficient way to encode an input 3D point cloud to the latent space of the SP-GAN. Our point cloud encoder can resolve the point ordering issue during inversion, and thus can determine the correspondences between points in the generated 3D point cloud and those in the canonical sphere used by the generator. We show that our method outperforms previous GAN inversion methods for 3D point clouds, achieving state-of-the-art results both quantitatively and qualitatively. Our code is available at https://github.com/hkust-vgd/point_inverter.