# Point Cloud Completion by Learning Shape Priors

arXiv: https://arxiv.org/abs/2008.00394 · HTML: https://mlsanity.com/paper/2008.00394/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Aug 2020.

## Built on by (most cited first, 14 of 14)

- [3D Semantic Scene Completion: a Survey](https://mlsanity.com/paper/2103.07466/) (2021)
- [Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis](https://mlsanity.com/paper/2203.03311/) (2022)
- [Voxel-based Network for Shape Completion by Leveraging Edge Generation](https://mlsanity.com/paper/2108.09936/) (2021)
- [Orienting Point Clouds with Dipole Propagation](https://mlsanity.com/paper/2105.01604/) (2021)
- [LiDAR-based 4D Occupancy Completion and Forecasting](https://mlsanity.com/paper/2310.11239/) (2023)
- [Self-Supervised Point Cloud Completion via Inpainting](https://mlsanity.com/paper/2111.10701/) (2021)
- [NeuralBlox: Real-Time Neural Representation Fusion for Robust Volumetric Mapping](https://mlsanity.com/paper/2110.09415/) (2021)
- [SCARP: 3D Shape Completion in ARbitrary Poses for Improved Grasping](https://mlsanity.com/paper/2301.07213/) (2023)
- [GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer](https://mlsanity.com/paper/2408.06596/) (2024)
- [FSC: Few-point Shape Completion](https://mlsanity.com/paper/2403.07359/) (2024)
- [Underground Mapping and Localization Based on Ground-Penetrating Radar](https://mlsanity.com/paper/2409.16446/) (2024)
- [SPAC-Net: Rethinking Point Cloud Completion with Structural Prior](https://mlsanity.com/paper/2411.15066/) (2024)
- [CarveNet: Carving Point-Block for Complex 3D Shape Completion](https://mlsanity.com/paper/2107.13452/) (2021)
- [3D Reconstruction Techniques in the Manufacturing Domain: Applications, Research Opportunities and Use Cases](https://mlsanity.com/paper/2604.28064/) (2026)

## Abstract (arXiv)

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.