# Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Clouds

arXiv: https://arxiv.org/abs/2203.16001 · HTML: https://mlsanity.com/paper/2203.16001/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 47 references that are in the map.
- First posted on arXiv 30 Mar 2022.

## Builds on (most cited first, 30 of 42)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework](https://mlsanity.com/paper/2202.07123/) (2022)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)
- [How to train your MAML](https://mlsanity.com/paper/1810.09502/) (2018)
- [PREDATOR: Registration of 3D Point Clouds with Low Overlap](https://mlsanity.com/paper/2011.13005/) (2020)
- [Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs](https://mlsanity.com/paper/1703.09438/) (2017)
- [Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis](https://mlsanity.com/paper/2105.01288/) (2021)
- [The Perfect Match: 3D Point Cloud Matching with Smoothed Densities](https://mlsanity.com/paper/1811.06879/) (2018)
- [Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline](https://mlsanity.com/paper/2106.05304/) (2021)
- [SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration](https://mlsanity.com/paper/2011.12149/) (2020)
- [MVTN: Multi-View Transformation Network for 3D Shape Recognition](https://mlsanity.com/paper/2011.13244/) (2020)
- [Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds](https://mlsanity.com/paper/2203.11139/) (2022)
- [Grid-GCN for Fast and Scalable Point Cloud Learning](https://mlsanity.com/paper/1912.02984/) (2019)
- [Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network](https://mlsanity.com/paper/1811.02565/) (2018)
- [SampleNet: Differentiable Point Cloud Sampling](https://mlsanity.com/paper/1912.03663/) (2019)

## Built on by (most cited first, 6 of 6)

- [Adaptive LiDAR Scanning: Harnessing Temporal Cues for Efficient 3D Object Detection via Multi-Modal Fusion](https://mlsanity.com/paper/2508.01562/) (2025)
- [Towards a GML-Enabled Knowledge Graph Platform](https://mlsanity.com/paper/2303.02166/) (2023)
- [Hierarchical Adaptive Voxel-guided Sampling for Real-time Applications in Large-scale Point Clouds](https://mlsanity.com/paper/2305.14306/) (2023)
- [REPS: Reconstruction-based Point Cloud Sampling](https://mlsanity.com/paper/2403.05047/) (2024)
- [MorphoSkel3D: Morphological Skeletonization of 3D Point Clouds for Informed Sampling in Object Classification and Retrieval](https://mlsanity.com/paper/2501.12974/) (2025)
- [Discretizing Group-Convolutional Neural Networks for 3D Geometry in Feature Space](https://mlsanity.com/paper/2605.15368/) (2026)

## Abstract (arXiv)

Sampling is a key operation in point-cloud task and acts to increase computational efficiency and tractability by discarding redundant points. Universal sampling algorithms (e.g., Farthest Point Sampling) work without modification across different tasks, models, and datasets, but by their very nature are agnostic about the downstream task/model. As such, they have no implicit knowledge about which points would be best to keep and which to reject. Recent work has shown how task-specific point cloud sampling (e.g., SampleNet) can be used to outperform traditional sampling approaches by learning which points are more informative. However, these learnable samplers face two inherent issues: i) overfitting to a model rather than a task, and ii) requiring training of the sampling network from scratch, in addition to the task network, somewhat countering the original objective of down-sampling to increase efficiency. In this work, we propose an almost-universal sampler, in our quest for a sampler that can learn to preserve the most useful points for a particular task, yet be inexpensive to adapt to different tasks, models, or datasets. We first demonstrate how training over multiple models for the same task (e.g., shape reconstruction) significantly outperforms the vanilla SampleNet in terms of accuracy by not overfitting the sample network to a particular task network. Second, we show how we can train an almost-universal meta-sampler across multiple tasks. This meta-sampler can then be rapidly fine-tuned when applied to different datasets, networks, or even different tasks, thus amortizing the initial cost of training.