# ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding

arXiv: https://arxiv.org/abs/2312.11112 · HTML: https://mlsanity.com/paper/2312.11112/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 84 of its 99 references that are in the map.
- First posted on arXiv 18 Dec 2023.

## Builds on (most cited first, 30 of 84)

- [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)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (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)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows](https://mlsanity.com/paper/2107.00652/) (2021)
- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://mlsanity.com/paper/2203.11496/) (2022)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)

## Built on by (most cited first, 16 of 16)

- [UniMix: Towards Domain Adaptive and Generalizable LiDAR Semantic Segmentation in Adverse Weather](https://mlsanity.com/paper/2404.05145/) (2024)
- [LitePT: Lighter Yet Stronger Point Transformer](https://mlsanity.com/paper/2512.13689/) (2025)
- [Local-consistent Transformation Learning for Rotation-invariant Point Cloud Analysis](https://mlsanity.com/paper/2403.11113/) (2024)
- [Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis](https://mlsanity.com/paper/2410.20406/) (2024)
- [BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis](https://mlsanity.com/paper/2503.12539/) (2025)
- [Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis](https://mlsanity.com/paper/2503.12150/) (2025)
- [On-the-fly Point Feature Representation for Point Clouds Analysis](https://mlsanity.com/paper/2407.21335/) (2024)
- [PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2503.06094/) (2025)
- [STP4D: Spatio-Temporal-Prompt Consistent Modeling for Text-to-4D Gaussian Splatting](https://mlsanity.com/paper/2504.18318/) (2025)
- [HydraMamba: Multi-Head State Space Model for Global Point Cloud Learning](https://mlsanity.com/paper/2507.19778/) (2025)
- [HyperPointFormer: Multimodal Fusion in 3D Space with Dual-Branch Cross-Attention Transformers](https://mlsanity.com/paper/2505.23206/) (2025)
- [Enhancing point cloud analysis via neighbor aggregation correction based on cross-stage structure correlation](https://mlsanity.com/paper/2506.15160/) (2025)
- [High-quality Pseudo-labeling for Point Cloud Segmentation with Scene-level Annotation](https://mlsanity.com/paper/2506.23227/) (2025)
- [GeoPurify: A Data-Efficient Geometric Distillation Framework for Open-Vocabulary 3D Segmentation](https://mlsanity.com/paper/2510.02186/) (2025)
- [Soft Masked Transformer for Point Cloud Processing with Skip Attention-Based Upsampling](https://mlsanity.com/paper/2403.14124/) (2024)
- [Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis](https://mlsanity.com/paper/2509.00374/) (2025)

## Abstract (arXiv)

Transformers have been recently explored for 3D point cloud understanding with impressive progress achieved. A large number of points, over 0.1 million, make the global self-attention infeasible for point cloud data. Thus, most methods propose to apply the transformer in a local region, e.g., spherical or cubic window. However, it still contains a large number of Query-Key pairs, which requires high computational costs. In addition, previous methods usually learn the query, key, and value using a linear projection without modeling the local 3D geometric structure. In this paper, we attempt to reduce the costs and model the local geometry prior by developing a new transformer block, named ConDaFormer. Technically, ConDaFormer disassembles the cubic window into three orthogonal 2D planes, leading to fewer points when modeling the attention in a similar range. The disassembling operation is beneficial to enlarging the range of attention without increasing the computational complexity, but ignores some contexts. To provide a remedy, we develop a local structure enhancement strategy that introduces a depth-wise convolution before and after the attention. This scheme can also capture the local geometric information. Taking advantage of these designs, ConDaFormer captures both long-range contextual information and local priors. The effectiveness is demonstrated by experimental results on several 3D point cloud understanding benchmarks. Code is available at https://github.com/LHDuan/ConDaFormer .