# Hypernetwork approach to generating point clouds

arXiv: https://arxiv.org/abs/2003.00802 · HTML: https://mlsanity.com/paper/2003.00802/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2020.

## Built on by (most cited first, 20 of 20)

- [A Brief Review of Hypernetworks in Deep Learning](https://mlsanity.com/paper/2306.06955/) (2023)
- [Generative Models as Distributions of Functions](https://mlsanity.com/paper/2102.04776/) (2021)
- [Learning the Effect of Registration Hyperparameters with HyperMorph](https://mlsanity.com/paper/2203.16680/) (2022)
- [Gaussian Splatting with NeRF-based Color and Opacity](https://mlsanity.com/paper/2312.13729/) (2023)
- [HyperDet3D: Learning a Scene-conditioned 3D Object Detector](https://mlsanity.com/paper/2204.05599/) (2022)
- [HyperPocket: Generative Point Cloud Completion](https://mlsanity.com/paper/2102.05973/) (2021)
- [HyperSound: Generating Implicit Neural Representations of Audio Signals with Hypernetworks](https://mlsanity.com/paper/2211.01839/) (2022)
- [Points2NeRF: Generating Neural Radiance Fields from 3D point cloud](https://mlsanity.com/paper/2206.01290/) (2022)
- [Hypernetworks build Implicit Neural Representations of Sounds](https://mlsanity.com/paper/2302.04959/) (2023)
- [HyperTab: Hypernetwork Approach for Deep Learning on Small Tabular Datasets](https://mlsanity.com/paper/2304.03543/) (2023)
- [HyperNeRFGAN: Hypernetwork approach to 3D NeRF GAN](https://mlsanity.com/paper/2301.11631/) (2023)
- [InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules](https://mlsanity.com/paper/2308.13897/) (2023)
- [HyperCube: Implicit Field Representations of Voxelized 3D Models](https://mlsanity.com/paper/2110.05770/) (2021)
- [HyperMask: Adaptive Hypernetwork-based Masks for Continual Learning](https://mlsanity.com/paper/2310.00113/) (2023)
- [Modeling 3D Surface Manifolds with a Locally Conditioned Atlas](https://mlsanity.com/paper/2102.05984/) (2021)
- [HyperColor: A HyperNetwork Approach for Synthesizing Auto-colored 3D Models for Game Scenes Population](https://mlsanity.com/paper/2108.01411/) (2021)
- [Implicit Neural Representation For Accurate CFD Flow Field Prediction](https://mlsanity.com/paper/2408.06486/) (2024)
- [Ensuring Semantics in Weights of Implicit Neural Representations through the Implicit Function Theorem](https://mlsanity.com/paper/2601.23181/) (2026)
- [Robust MIMO Detection using Hypernetworks with Learned Regularizers](https://mlsanity.com/paper/2110.07053/) (2021)
- [OmniStyle-INR: Universal and Multimodal Style Transfer for INRs](https://mlsanity.com/paper/2607.16362/) (2026)

## Abstract (arXiv)

In this work, we propose a novel method for generating 3D point clouds that leverage properties of hyper networks. Contrary to the existing methods that learn only the representation of a 3D object, our approach simultaneously finds a representation of the object and its 3D surface. The main idea of our HyperCloud method is to build a hyper network that returns weights of a particular neural network (target network) trained to map points from a uniform unit ball distribution into a 3D shape. As a consequence, a particular 3D shape can be generated using point-by-point sampling from the assumed prior distribution and transforming sampled points with the target network. Since the hyper network is based on an auto-encoder architecture trained to reconstruct realistic 3D shapes, the target network weights can be considered a parametrization of the surface of a 3D shape, and not a standard representation of point cloud usually returned by competitive approaches. The proposed architecture allows finding mesh-based representation of 3D objects in a generative manner while providing point clouds en pair in quality with the state-of-the-art methods.