# CS-Net:Contribution-based Sampling Network for Point Cloud Simplification

arXiv: https://arxiv.org/abs/2501.10789 · HTML: https://mlsanity.com/paper/2501.10789/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 44 references that are in the map.
- First posted on arXiv 18 Jan 2025.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (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)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection](https://mlsanity.com/paper/2012.15712/) (2020)
- [PU-GAN: a Point Cloud Upsampling Adversarial Network](https://mlsanity.com/paper/1907.10844/) (2019)
- [Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration](https://mlsanity.com/paper/1605.03344/) (2016)
- [Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling](https://mlsanity.com/paper/1904.03375/) (2019)
- [Differentiable Ranks and Sorting using Optimal Transport](https://mlsanity.com/paper/1905.11885/) (2019)
- [SampleNet: Differentiable Point Cloud Sampling](https://mlsanity.com/paper/1912.03663/) (2019)
- [A Rotation-Invariant Framework for Deep Point Cloud Analysis](https://mlsanity.com/paper/2003.07238/) (2020)
- [Imperceptible Transfer Attack and Defense on 3D Point Cloud Classification](https://mlsanity.com/paper/2111.10990/) (2021)
- [Deep Magnification-Flexible Upsampling over 3D Point Clouds](https://mlsanity.com/paper/2011.12745/) (2020)
- [Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation](https://mlsanity.com/paper/2308.14619/) (2023)
- [PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling](https://mlsanity.com/paper/2203.00914/) (2022)
- [Differentiable Top-k Operator with Optimal Transport](https://mlsanity.com/paper/2002.06504/) (2020)
- [PU-Flow: a Point Cloud Upsampling Network with Normalizing Flows](https://mlsanity.com/paper/2107.05893/) (2021)
- [PnP-3D: A Plug-and-Play for 3D Point Clouds](https://mlsanity.com/paper/2108.07378/) (2021)
- [Revisiting Point Cloud Simplification: A Learnable Feature Preserving Approach](https://mlsanity.com/paper/2109.14982/) (2021)

## Built on by (most cited first, 3 of 3)

- [PCE-GAN: A Generative Adversarial Network for Point Cloud Attribute Quality Enhancement based on Optimal Transport](https://mlsanity.com/paper/2503.00047/) (2025)
- [Rate-distortion Optimized Point Cloud Preprocessing for Geometry-based Point Cloud Compression](https://mlsanity.com/paper/2508.01633/) (2025)
- [Fast Attention-Based Simplification of LiDAR Point Clouds for Object Detection and Classification](https://mlsanity.com/paper/2603.07593/) (2026)

## Abstract (arXiv)

Point cloud sampling plays a crucial role in reducing computation costs and storage requirements for various vision tasks. Traditional sampling methods, such as farthest point sampling, lack task-specific information and, as a result, cannot guarantee optimal performance in specific applications. Learning-based methods train a network to sample the point cloud for the targeted downstream task. However, they do not guarantee that the sampled points are the most relevant ones. Moreover, they may result in duplicate sampled points, which requires completion of the sampled point cloud through post-processing techniques. To address these limitations, we propose a contribution-based sampling network (CS-Net), where the sampling operation is formulated as a Top-k operation. To ensure that the network can be trained in an end-to-end way using gradient descent algorithms, we use a differentiable approximation to the Top-k operation via entropy regularization of an optimal transport problem. Our network consists of a feature embedding module, a cascade attention module, and a contribution scoring module. The feature embedding module includes a specifically designed spatial pooling layer to reduce parameters while preserving important features. The cascade attention module combines the outputs of three skip connected offset attention layers to emphasize the attractive features and suppress less important ones. The contribution scoring module generates a contribution score for each point and guides the sampling process to prioritize the most important ones. Experiments on the ModelNet40 and PU147 showed that CS-Net achieved state-of-the-art performance in two semantic-based downstream tasks (classification and registration) and two reconstruction-based tasks (compression and surface reconstruction).