# Self-Sampling for Neural Point Cloud Consolidation

arXiv: https://arxiv.org/abs/2008.06471 · HTML: https://mlsanity.com/paper/2008.06471/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2020.

## Built on by (most cited first, 15 of 15)

- [Text2Mesh: Text-Driven Neural Stylization for Meshes](https://mlsanity.com/paper/2112.03221/) (2021)
- [Orienting Point Clouds with Dipole Propagation](https://mlsanity.com/paper/2105.01604/) (2021)
- [PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling](https://mlsanity.com/paper/2203.00914/) (2022)
- [Deep Internal Learning: Deep Learning from a Single Input](https://mlsanity.com/paper/2312.07425/) (2023)
- [NeuralMLS: Geometry-Aware Control Point Deformation](https://mlsanity.com/paper/2201.01873/) (2022)
- [iPUNet:Iterative Cross Field Guided Point Cloud Upsampling](https://mlsanity.com/paper/2310.09092/) (2023)
- [Efficient Point Clouds Upsampling via Flow Matching](https://mlsanity.com/paper/2501.15286/) (2025)
- [A dataset-free approach for self-supervised learning of 3D reflectional symmetries](https://mlsanity.com/paper/2503.02660/) (2025)
- [Z2P: Instant Visualization of Point Clouds](https://mlsanity.com/paper/2105.14548/) (2021)
- [U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching](https://mlsanity.com/paper/2510.25210/) (2025)
- [Learning Self-Prior for Mesh Inpainting Using Self-Supervised Graph Convolutional Networks](https://mlsanity.com/paper/2305.00635/) (2023)
- [Deep Point Cloud Simplification for High-quality Surface Reconstruction](https://mlsanity.com/paper/2203.09088/) (2022)
- [Curvature Informed Furthest Point Sampling](https://mlsanity.com/paper/2411.16995/) (2024)
- [AS-PD: An Arbitrary-Size Downsampling Framework for Point Clouds](https://mlsanity.com/paper/2211.01110/) (2022)
- [EdgeFormer: local patch-based edge detection transformer on point clouds](https://mlsanity.com/paper/2604.21387/) (2026)

## Abstract (arXiv)

We introduce a novel technique for neural point cloud consolidation which learns from only the input point cloud. Unlike other point upsampling methods which analyze shapes via local patches, in this work, we learn from global subsets. We repeatedly self-sample the input point cloud with global subsets that are used to train a deep neural network. Specifically, we define source and target subsets according to the desired consolidation criteria (e.g., generating sharp points or points in sparse regions). The network learns a mapping from source to target subsets, and implicitly learns to consolidate the point cloud. During inference, the network is fed with random subsets of points from the input, which it displaces to synthesize a consolidated point set. We leverage the inductive bias of neural networks to eliminate noise and outliers, a notoriously difficult problem in point cloud consolidation. The shared weights of the network are optimized over the entire shape, learning non-local statistics and exploiting the recurrence of local-scale geometries. Specifically, the network encodes the distribution of the underlying shape surface within a fixed set of local kernels, which results in the best explanation of the underlying shape surface. We demonstrate the ability to consolidate point sets from a variety of shapes, while eliminating outliers and noise.