# PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation

arXiv: https://arxiv.org/abs/1807.00652 · HTML: https://mlsanity.com/paper/1807.00652/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2018.

## Built on by (most cited first, 30 of 58)

- [Multi-Modal 3D Object Detection in Autonomous Driving: a Survey](https://mlsanity.com/paper/2106.12735/) (2021)
- [STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset](https://mlsanity.com/paper/2203.09065/) (2022)
- [Attention-based Point Cloud Edge Sampling](https://mlsanity.com/paper/2302.14673/) (2023)
- [Deep Learning Based 3D Segmentation: A Survey](https://mlsanity.com/paper/2103.05423/) (2021)
- [Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes](https://mlsanity.com/paper/2208.06671/) (2022)
- [General Place Recognition Survey: Towards Real-World Autonomy](https://mlsanity.com/paper/2405.04812/) (2024)
- [Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2410.22489/) (2024)
- [Rethinking Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2403.00592/) (2024)
- [Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification](https://mlsanity.com/paper/2207.10278/) (2022)
- [Sim2real Transfer Learning for Point Cloud Segmentation: An Industrial Application Case on Autonomous Disassembly](https://mlsanity.com/paper/2301.05033/) (2023)
- [RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation](https://mlsanity.com/paper/2407.10159/) (2024)
- [GA-NET: Global Attention Network for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2107.03101/) (2021)
- [HiTPR: Hierarchical Transformer for Place Recognition in Point Cloud](https://mlsanity.com/paper/2204.05481/) (2022)
- [GeoSegNet: Point Cloud Semantic Segmentation via Geometric Encoder-Decoder Modeling](https://mlsanity.com/paper/2207.06766/) (2022)
- [DLA-Net: Learning Dual Local Attention Features for Semantic Segmentation of Large-Scale Building Facade Point Clouds](https://mlsanity.com/paper/2106.00376/) (2021)
- [Language-Level Semantics Conditioned 3D Point Cloud Segmentation](https://mlsanity.com/paper/2107.00430/) (2021)
- [GSIP: Green Semantic Segmentation of Large-Scale Indoor Point Clouds](https://mlsanity.com/paper/2109.11835/) (2021)
- [Investigate Indistinguishable Points in Semantic Segmentation of 3D Point Cloud](https://mlsanity.com/paper/2103.10339/) (2021)
- [MKConv: Multidimensional Feature Representation for Point Cloud Analysis](https://mlsanity.com/paper/2107.12655/) (2021)
- [Sequential Point Clouds: A Survey](https://mlsanity.com/paper/2204.09337/) (2022)
- [Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities](https://mlsanity.com/paper/2212.02287/) (2022)
- [Dense Graph Convolutional Neural Networks on 3D Meshes for 3D Object Segmentation and Classification](https://mlsanity.com/paper/2106.15778/) (2021)
- [Understanding the Challenges When 3D Semantic Segmentation Faces Class Imbalanced and OOD Data](https://mlsanity.com/paper/2203.00214/) (2022)
- [LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectives](https://mlsanity.com/paper/2503.18384/) (2025)
- [Similarity-Aware Fusion Network for 3D Semantic Segmentation](https://mlsanity.com/paper/2107.01579/) (2021)
- [Differentiable Convolution Search for Point Cloud Processing](https://mlsanity.com/paper/2108.12856/) (2021)
- [Semantic Segmentation for Point Cloud Scenes via Dilated Graph Feature Aggregation and Pyramid Decoders](https://mlsanity.com/paper/2204.04944/) (2022)
- [Learning Spatial and Temporal Variations for 4D Point Cloud Segmentation](https://mlsanity.com/paper/2207.04673/) (2022)
- [Advancements in Point Cloud-Based 3D Defect Detection and Classification for Industrial Systems: A Comprehensive Survey](https://mlsanity.com/paper/2402.12923/) (2024)
- [On-the-fly Point Feature Representation for Point Clouds Analysis](https://mlsanity.com/paper/2407.21335/) (2024)

## Abstract (arXiv)

Recently, 3D understanding research sheds light on extracting features from point cloud directly, which requires effective shape pattern description of point clouds. Inspired by the outstanding 2D shape descriptor SIFT, we design a module called PointSIFT that encodes information of different orientations and is adaptive to scale of shape. Specifically, an orientation-encoding unit is designed to describe eight crucial orientations, and multi-scale representation is achieved by stacking several orientation-encoding units. PointSIFT module can be integrated into various PointNet-based architecture to improve the representation ability. Extensive experiments show our PointSIFT-based framework outperforms state-of-the-art method on standard benchmark datasets. The code and trained model will be published accompanied by this paper.