arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2008.00394cs.CVcs.LGeess.IV
收藏

基于形状先验知识的点云数据拟合

Point Cloud Completion by Learning Shape Priors

National University of Singapore(新加坡国立大学)

Xiaogang Wang, Marcelo H Ang, Gim Hee Lee

摘要:

针对点云补全中物体细节重建困难的问题,提出了一种基于形状先验学习的物体补全方法。形状先验包括完整点云和部分点云中的几何信息。我们设计了一个特征对齐策略,从完整的点学习形状先验,和一个粗到精的策略,将部分先验的精细阶段。为了事先学习完整的对象,我们首先训练一个点云自动编码器来从完整的点中提取潜在的嵌入。然后我们学习一个映射,通过优化特征对齐损失将点特征从部分点转移到完整点。特征对齐损失由L2距离和由最大均值离散生成对抗网络(MMD-GAN)获得的对抗损失组成。L2距离优化了特征空间中的部分特征,MMD-GAN减小了再生核希尔伯特空间中两个点特征的统计距离。我们在点云完成任务上实现了最先进的性能。我们的代码可在https://github.com/xiaogangw/point-cloud-completion-shape-prior上获得。

英文摘要:

In view of the difficulty in reconstructing object details in point cloud completion, we propose a shape prior learning method for object completion. The shape priors include geometric information in both complete and the partial point clouds. We design a feature alignment strategy to learn the shape prior from complete points, and a coarse to fine strategy to incorporate partial prior in the fine stage. To learn the complete objects prior, we first train a point cloud auto-encoder to extract the latent embeddings from complete points. Then we learn a mapping to transfer the point features from partial points to that of the complete points by optimizing feature alignment losses. The feature alignment losses consist of a L2 distance and an adversarial loss obtained by Maximum Mean Discrepancy Generative Adversarial Network (MMD-GAN). The L2 distance optimizes the partial features towards the complete ones in the feature space, and MMD-GAN decreases the statistical distance of two point features in a Reproducing Kernel Hilbert Space. We achieve state-of-the-art performances on the point cloud completion task. Our code is available at https://github.com/xiaogangw/point-cloud-completion-shape-prior.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑