# HyperPocket: Generative Point Cloud Completion

arXiv: https://arxiv.org/abs/2102.05973 · HTML: https://mlsanity.com/paper/2102.05973/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 39 references that are in the map.
- First posted on arXiv 11 Feb 2021.

## Builds on (most cited first, 29 of 29)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generation](https://mlsanity.com/paper/1802.05384/) (2018)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows](https://mlsanity.com/paper/1906.12320/) (2019)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis](https://mlsanity.com/paper/1612.00101/) (2016)
- [GRNet: Gridding Residual Network for Dense Point Cloud Completion](https://mlsanity.com/paper/2006.03761/) (2020)
- [Morphing and Sampling Network for Dense Point Cloud Completion](https://mlsanity.com/paper/1912.00280/) (2019)
- [Unsupervised Multi-Task Feature Learning on Point Clouds](https://mlsanity.com/paper/1910.08207/) (2019)
- [High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference](https://mlsanity.com/paper/1709.07599/) (2017)
- [Interpolated Convolutional Networks for 3D Point Cloud Understanding](https://mlsanity.com/paper/1908.04512/) (2019)
- [Unpaired Point Cloud Completion on Real Scans using Adversarial Training](https://mlsanity.com/paper/1904.00069/) (2019)
- [Hypernetwork functional image representation](https://mlsanity.com/paper/1902.10404/) (2019)
- [Multimodal Shape Completion via Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2003.07717/) (2020)
- [Octree guided CNN with Spherical Kernels for 3D Point Clouds](https://mlsanity.com/paper/1903.00343/) (2019)
- [Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Network](https://mlsanity.com/paper/1901.08906/) (2019)
- [Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features](https://mlsanity.com/paper/1904.10014/) (2019)
- [Review: deep learning on 3D point clouds](https://mlsanity.com/paper/2001.06280/) (2020)
- [Hypernetwork approach to generating point clouds](https://mlsanity.com/paper/2003.00802/) (2020)
- [Stochastic Maximum Likelihood Optimization via Hypernetworks](https://mlsanity.com/paper/1712.01141/) (2017)
- [HyperFlow: Representing 3D Objects as Surfaces](https://mlsanity.com/paper/2006.08710/) (2020)
- [Generate What You Can't See - a View-dependent Image Generation](https://mlsanity.com/paper/1903.06814/) (2019)

## Built on by (most cited first, 12 of 12)

- [HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing](https://mlsanity.com/paper/2111.15666/) (2021)
- [Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis](https://mlsanity.com/paper/2203.03311/) (2022)
- [Points2NeRF: Generating Neural Radiance Fields from 3D point cloud](https://mlsanity.com/paper/2206.01290/) (2022)
- [HyperCube: Implicit Field Representations of Voxelized 3D Models](https://mlsanity.com/paper/2110.05770/) (2021)
- [HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Models](https://mlsanity.com/paper/2601.15968/) (2026)
- [INFAMOUS-NeRF: ImproviNg FAce MOdeling Using Semantically-Aligned Hypernetworks with Neural Radiance Fields](https://mlsanity.com/paper/2312.16197/) (2023)
- [Completing Partial Point Clouds with Outliers by Collaborative Completion and Segmentation](https://mlsanity.com/paper/2203.09772/) (2022)
- [3D objects and scenes classification, recognition, segmentation, and reconstruction using 3D point cloud data: A review](https://mlsanity.com/paper/2306.05978/) (2023)
- [HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset](https://mlsanity.com/paper/2303.02610/) (2023)
- [Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose Estimation](https://mlsanity.com/paper/2403.12728/) (2024)
- [GPN: Generative Point-based NeRF](https://mlsanity.com/paper/2404.08312/) (2024)
- [Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones](https://mlsanity.com/paper/2506.05641/) (2025)

## Abstract (arXiv)

Scanning real-life scenes with modern registration devices typically give incomplete point cloud representations, mostly due to the limitations of the scanning process and 3D occlusions. Therefore, completing such partial representations remains a fundamental challenge of many computer vision applications. Most of the existing approaches aim to solve this problem by learning to reconstruct individual 3D objects in a synthetic setup of an uncluttered environment, which is far from a real-life scenario. In this work, we reformulate the problem of point cloud completion into an object hallucination task. Thus, we introduce a novel autoencoder-based architecture called HyperPocket that disentangles latent representations and, as a result, enables the generation of multiple variants of the completed 3D point clouds. We split point cloud processing into two disjoint data streams and leverage a hypernetwork paradigm to fill the spaces, dubbed pockets, that are left by the missing object parts. As a result, the generated point clouds are not only smooth but also plausible and geometrically consistent with the scene. Our method offers competitive performances to the other state-of-the-art models, and it enables a~plethora of novel applications.