# Cloud Transformers: A Universal Approach To Point Cloud Processing Tasks

arXiv: https://arxiv.org/abs/2007.11679 · HTML: https://mlsanity.com/paper/2007.11679/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jul 2020.

## Built on by (most cited first, 24 of 24)

- [PointMixer: MLP-Mixer for Point Cloud Understanding](https://mlsanity.com/paper/2111.11187/) (2021)
- [Benchmarking and Analyzing Point Cloud Classification under Corruptions](https://mlsanity.com/paper/2202.03377/) (2022)
- [Self-positioning Point-based Transformer for Point Cloud Understanding](https://mlsanity.com/paper/2303.16450/) (2023)
- [PU-Transformer: Point Cloud Upsampling Transformer](https://mlsanity.com/paper/2111.12242/) (2021)
- [PartGlot: Learning Shape Part Segmentation from Language Reference Games](https://mlsanity.com/paper/2112.06390/) (2021)
- [3DCTN: 3D Convolution-Transformer Network for Point Cloud Classification](https://mlsanity.com/paper/2203.00828/) (2022)
- [Clustering based Point Cloud Representation Learning for 3D Analysis](https://mlsanity.com/paper/2307.14605/) (2023)
- [Few-shot Class-incremental Learning for 3D Point Cloud Objects](https://mlsanity.com/paper/2205.15225/) (2022)
- [PointMCD: Boosting Deep Point Cloud Encoders via Multi-view Cross-modal Distillation for 3D Shape Recognition](https://mlsanity.com/paper/2207.03128/) (2022)
- [Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition](https://mlsanity.com/paper/2204.03957/) (2022)
- [PointWavelet: Learning in Spectral Domain for 3D Point Cloud Analysis](https://mlsanity.com/paper/2302.05201/) (2023)
- [Arbitrary Point Cloud Upsampling with Spherical Mixture of Gaussians](https://mlsanity.com/paper/2208.05274/) (2022)
- [Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2301.11145/) (2023)
- [Adaptive Local Basis Functions for Shape Completion](https://mlsanity.com/paper/2307.08348/) (2023)
- [GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentation](https://mlsanity.com/paper/2305.15213/) (2023)
- [Multi Point-Voxel Convolution (MPVConv) for Deep Learning on Point Clouds](https://mlsanity.com/paper/2107.13152/) (2021)
- [Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation](https://mlsanity.com/paper/2304.14124/) (2023)
- [HydraMamba: Multi-Head State Space Model for Global Point Cloud Learning](https://mlsanity.com/paper/2507.19778/) (2025)
- [Point Cloud Recognition with Position-to-Structure Attention Transformers](https://mlsanity.com/paper/2210.02030/) (2022)
- [Sampled Transformer for Point Sets](https://mlsanity.com/paper/2302.14346/) (2023)
- [3DGTN: 3D Dual-Attention GLocal Transformer Network for Point Cloud Classification and Segmentation](https://mlsanity.com/paper/2209.11255/) (2022)
- [Patch-Wise Point Cloud Generation: A Divide-and-Conquer Approach](https://mlsanity.com/paper/2307.12049/) (2023)
- [Global Attention-Guided Dual-Domain Point Cloud Feature Learning for Classification and Segmentation](https://mlsanity.com/paper/2407.08994/) (2024)
- [TCATSeg: A Tooth Center-Wise Attention Network for 3D Dental Model Semantic Segmentation](https://mlsanity.com/paper/2603.16620/) (2026)

## Abstract (arXiv)

We present a new versatile building block for deep point cloud processing architectures that is equally suited for diverse tasks. This building block combines the ideas of spatial transformers and multi-view convolutional networks with the efficiency of standard convolutional layers in two and three-dimensional dense grids. The new block operates via multiple parallel heads, whereas each head differentiably rasterizes feature representations of individual points into a low-dimensional space, and then uses dense convolution to propagate information across points. The results of the processing of individual heads are then combined together resulting in the update of point features. Using the new block, we build architectures for both discriminative (point cloud segmentation, point cloud classification) and generative (point cloud inpainting and image-based point cloud reconstruction) tasks. The resulting architectures achieve state-of-the-art performance for these tasks, demonstrating the versatility of the new block for point cloud processing.