# High Fidelity Semantic Shape Completion for Point Clouds using Latent Optimization

arXiv: https://arxiv.org/abs/1807.03407 · HTML: https://mlsanity.com/paper/1807.03407/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2018.

## Built on by (most cited first, 9 of 9)

- [Learning Smooth Neural Functions via Lipschitz Regularization](https://mlsanity.com/paper/2202.08345/) (2022)
- [Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis](https://mlsanity.com/paper/2203.03311/) (2022)
- [Orienting Point Clouds with Dipole Propagation](https://mlsanity.com/paper/2105.01604/) (2021)
- [ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion](https://mlsanity.com/paper/2104.09587/) (2021)
- [Mending Neural Implicit Modeling for 3D Vehicle Reconstruction in the Wild](https://mlsanity.com/paper/2101.06860/) (2021)
- [3DSGrasp: 3D Shape-Completion for Robotic Grasp](https://mlsanity.com/paper/2301.00866/) (2023)
- [TSCom-Net: Coarse-to-Fine 3D Textured Shape Completion Network](https://mlsanity.com/paper/2208.08768/) (2022)
- [Representation Learning of Point Cloud Upsampling in Global and Local Inputs](https://mlsanity.com/paper/2501.07076/) (2025)
- [Denoising-While-Completing Network (DWCNet): Robust Point Cloud Completion Under Corruption](https://mlsanity.com/paper/2507.16743/) (2025)

## Abstract (arXiv)

Semantic shape completion is a challenging problem in 3D computer vision where the task is to generate a complete 3D shape using a partial 3D shape as input. We propose a learning-based approach to complete incomplete 3D shapes through generative modeling and latent manifold optimization. Our algorithm works directly on point clouds. We use an autoencoder and a GAN to learn a distribution of embeddings for point clouds of object classes. An input point cloud with missing regions is first encoded to a feature vector. The representations learnt by the GAN are then used to find the best latent vector on the manifold using a combined optimization that finds a vector in the manifold of plausible vectors that is close to the original input (both in the feature space and the output space of the decoder). Experiments show that our algorithm is capable of successfully reconstructing point clouds with large missing regions with very high fidelity without having to rely on exemplar based database retrieval.