# DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing

arXiv: https://arxiv.org/abs/1909.03669 · HTML: https://mlsanity.com/paper/1909.03669/

## Key facts

- Cited by 104 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2019.

## Built on by (most cited first, 30 of 104)

- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework](https://mlsanity.com/paper/2202.07123/) (2022)
- [ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding](https://mlsanity.com/paper/2212.05171/) (2022)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds](https://mlsanity.com/paper/2103.14635/) (2021)
- [ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding](https://mlsanity.com/paper/2305.08275/) (2023)
- [Stratified Transformer for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2203.14508/) (2022)
- [Masked Discrimination for Self-Supervised Learning on Point Clouds](https://mlsanity.com/paper/2203.11183/) (2022)
- [Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline](https://mlsanity.com/paper/2106.05304/) (2021)
- [Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?](https://mlsanity.com/paper/2212.08320/) (2022)
- [Surface Representation for Point Clouds](https://mlsanity.com/paper/2205.05740/) (2022)
- [Score-Based Point Cloud Denoising](https://mlsanity.com/paper/2107.10981/) (2021)
- [PointMixer: MLP-Mixer for Point Cloud Understanding](https://mlsanity.com/paper/2111.11187/) (2021)
- [PointCutMix: Regularization Strategy for Point Cloud Classification](https://mlsanity.com/paper/2101.01461/) (2021)
- [PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis](https://mlsanity.com/paper/2112.04903/) (2021)
- [OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation](https://mlsanity.com/paper/2403.14418/) (2024)
- [Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models](https://mlsanity.com/paper/2106.04180/) (2021)
- [PointBA: Towards Backdoor Attacks in 3D Point Cloud](https://mlsanity.com/paper/2103.16074/) (2021)
- [Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis](https://mlsanity.com/paper/2303.08134/) (2023)
- [A Unified Query-based Paradigm for Point Cloud Understanding](https://mlsanity.com/paper/2203.01252/) (2022)
- [CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations](https://mlsanity.com/paper/2208.10555/) (2022)
- [Learning Inner-Group Relations on Point Clouds](https://mlsanity.com/paper/2108.12468/) (2021)
- [Isometric 3D Adversarial Examples in the Physical World](https://mlsanity.com/paper/2210.15291/) (2022)
- [Deep Point Set Resampling via Gradient Fields](https://mlsanity.com/paper/2111.02045/) (2021)
- [Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2308.12113/) (2023)
- [3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis](https://mlsanity.com/paper/2112.04863/) (2021)
- [Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes](https://mlsanity.com/paper/2208.06671/) (2022)
- [Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks](https://mlsanity.com/paper/2202.07261/) (2022)
- [PartSTAD: 2D-to-3D Part Segmentation Task Adaptation](https://mlsanity.com/paper/2401.05906/) (2024)

## Abstract (arXiv)

Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable. A thorough grasp of the elusive shape requires sufficiently contextual semantic information, yet few works devote to this. Here we propose DensePoint, a general architecture to learn densely contextual representation for point cloud processing. Technically, it extends regular grid CNN to irregular point configuration by generalizing a convolution operator, which holds the permutation invariance of points, and achieves efficient inductive learning of local patterns. Architecturally, it finds inspiration from dense connection mode, to repeatedly aggregate multi-level and multi-scale semantics in a deep hierarchy. As a result, densely contextual information along with rich semantics, can be acquired by DensePoint in an organic manner, making it highly effective. Extensive experiments on challenging benchmarks across four tasks, as well as thorough model analysis, verify DensePoint achieves the state of the arts.