# Revisiting Point Cloud Simplification: A Learnable Feature Preserving Approach

arXiv: https://arxiv.org/abs/2109.14982 · HTML: https://mlsanity.com/paper/2109.14982/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 84 references that are in the map.
- First posted on arXiv 30 Sep 2021.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [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)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Hierarchical Graph Representation Learning with Differentiable Pooling](https://mlsanity.com/paper/1806.08804/) (2018)
- [Graph U-Nets](https://mlsanity.com/paper/1905.05178/) (2019)
- [Self-Attention Graph Pooling](https://mlsanity.com/paper/1904.08082/) (2019)
- [PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling](https://mlsanity.com/paper/2003.00492/) (2020)
- [SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels](https://mlsanity.com/paper/1711.08920/) (2017)
- [ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations](https://mlsanity.com/paper/1911.07979/) (2019)
- [Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation](https://mlsanity.com/paper/1908.01491/) (2019)
- [Towards Sparse Hierarchical Graph Classifiers](https://mlsanity.com/paper/1811.01287/) (2018)
- [AvatarMe: Realistically Renderable 3D Facial Reconstruction "in-the-wild"](https://mlsanity.com/paper/2003.13845/) (2020)
- [Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways](https://mlsanity.com/paper/2003.08284/) (2020)
- [SampleNet: Differentiable Point Cloud Sampling](https://mlsanity.com/paper/1912.03663/) (2019)
- [LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds](https://mlsanity.com/paper/1904.10037/) (2019)
- [Learning to Generate Customized Dynamic 3D Facial Expressions](https://mlsanity.com/paper/2007.09805/) (2020)
- [DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction](https://mlsanity.com/paper/1911.09204/) (2019)
- [Feature Preserving and Uniformity-controllable Point Cloud Simplification on Graph](https://mlsanity.com/paper/1812.11383/) (2018)
- [Spectral Coarsening of Geometric Operators](https://mlsanity.com/paper/1905.05161/) (2019)

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

- [SAGS: Structure-Aware 3D Gaussian Splatting](https://mlsanity.com/paper/2404.19149/) (2024)
- [GraphWalks: Efficient Shape Agnostic Geodesic Shortest Path Estimation](https://mlsanity.com/paper/2205.15217/) (2022)
- [Design2Cloth: 3D Cloth Generation from 2D Masks](https://mlsanity.com/paper/2404.02686/) (2024)
- [CS-Net:Contribution-based Sampling Network for Point Cloud Simplification](https://mlsanity.com/paper/2501.10789/) (2025)
- [ROSA: Reconstructing Object Shape and Appearance Textures by Adaptive Detail Transfer](https://mlsanity.com/paper/2501.18595/) (2025)
- [WrappingNet: Mesh Autoencoder via Deep Sphere Deformation](https://mlsanity.com/paper/2308.15413/) (2023)
- [GP-PCS: One-shot Feature-Preserving Point Cloud Simplification with Gaussian Processes on Riemannian Manifolds](https://mlsanity.com/paper/2303.15225/) (2023)
- [Generating Sizing Fields for Mesh Generation via GCN-based Simplification of Adaptive Background Grids](https://mlsanity.com/paper/2510.08645/) (2025)
- [Spinal Line Detection for Posture Evaluation through Train-ing-free 3D Human Body Reconstruction with 2D Depth Images](https://mlsanity.com/paper/2512.12718/) (2025)

## Abstract (arXiv)

The recent advances in 3D sensing technology have made possible the capture of point clouds in significantly high resolution. However, increased detail usually comes at the expense of high storage, as well as computational costs in terms of processing and visualization operations. Mesh and Point Cloud simplification methods aim to reduce the complexity of 3D models while retaining visual quality and relevant salient features. Traditional simplification techniques usually rely on solving a time-consuming optimization problem, hence they are impractical for large-scale datasets. In an attempt to alleviate this computational burden, we propose a fast point cloud simplification method by learning to sample salient points. The proposed method relies on a graph neural network architecture trained to select an arbitrary, user-defined, number of points from the input space and to re-arrange their positions so as to minimize the visual perception error. The approach is extensively evaluated on various datasets using several perceptual metrics. Importantly, our method is able to generalize to out-of-distribution shapes, hence demonstrating zero-shot capabilities.