# Deep Point Cloud Simplification for High-quality Surface Reconstruction

arXiv: https://arxiv.org/abs/2203.09088 · HTML: https://mlsanity.com/paper/2203.09088/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 47 references that are in the map.
- First posted on arXiv 17 Mar 2022.

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

- [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)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [PU-Net: Point Cloud Upsampling Network](https://mlsanity.com/paper/1801.06761/) (2018)
- [PU-GAN: a Point Cloud Upsampling Adversarial Network](https://mlsanity.com/paper/1907.10844/) (2019)
- [Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling](https://mlsanity.com/paper/1904.03375/) (2019)
- [Deep Geometric Prior for Surface Reconstruction](https://mlsanity.com/paper/1811.10943/) (2018)
- [Point Cloud Completion by Skip-attention Network with Hierarchical Folding](https://mlsanity.com/paper/2005.03871/) (2020)
- [Patch-based Progressive 3D Point Set Upsampling](https://mlsanity.com/paper/1811.11286/) (2018)
- [PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks](https://mlsanity.com/paper/1912.03264/) (2019)
- [EC-Net: an Edge-aware Point set Consolidation Network](https://mlsanity.com/paper/1807.06010/) (2018)
- [SampleNet: Differentiable Point Cloud Sampling](https://mlsanity.com/paper/1912.03663/) (2019)
- [Point Cloud Upsampling via Disentangled Refinement](https://mlsanity.com/paper/2106.04779/) (2021)
- [PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling](https://mlsanity.com/paper/2002.10277/) (2020)
- [Adaptive Hierarchical Down-Sampling for Point Cloud Classification](https://mlsanity.com/paper/1904.08506/) (2019)
- [Meta-PU: An Arbitrary-Scale Upsampling Network for Point Cloud](https://mlsanity.com/paper/2102.04317/) (2021)
- [Fast Resampling of 3D Point Clouds via Graphs](https://mlsanity.com/paper/1702.06397/) (2017)
- [Self-Sampling for Neural Point Cloud Consolidation](https://mlsanity.com/paper/2008.06471/) (2020)
- [Point Cloud Super Resolution with Adversarial Residual Graph Networks](https://mlsanity.com/paper/1908.02111/) (2019)

## Built on by (most cited first, 1 of 1)

- [Semantic Human Mesh Reconstruction with Textures](https://mlsanity.com/paper/2403.02561/) (2024)

## Abstract (arXiv)

The growing size of point clouds enlarges consumptions of storage, transmission, and computation of 3D scenes. Raw data is redundant, noisy, and non-uniform. Therefore, simplifying point clouds for achieving compact, clean, and uniform points is becoming increasingly important for 3D vision and graphics tasks. Previous learning based methods aim to generate fewer points for scene understanding, regardless of the quality of surface reconstruction, leading to results with low reconstruction accuracy and bad point distribution. In this paper, we propose a novel point cloud simplification network (PCS-Net) dedicated to high-quality surface mesh reconstruction while maintaining geometric fidelity. We first learn a sampling matrix in a feature-aware simplification module to reduce the number of points. Then we propose a novel double-scale resampling module to refine the positions of the sampled points, to achieve a uniform distribution. To further retain important shape features, an adaptive sampling strategy with a novel saliency loss is designed. With our PCS-Net, the input non-uniform and noisy point cloud can be simplified in a feature-aware manner, i.e., points near salient features are consolidated but still with uniform distribution locally. Experiments demonstrate the effectiveness of our method and show that we outperform previous simplification or reconstruction-oriented upsampling methods.