# Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud

arXiv: https://arxiv.org/abs/2212.04744 · HTML: https://mlsanity.com/paper/2212.04744/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 39 references that are in the map.
- First posted on arXiv 9 Dec 2022.

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

- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [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)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [SO-Net: Self-Organizing Network for Point Cloud Analysis](https://mlsanity.com/paper/1803.04249/) (2018)
- [SEGCloud: Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/1710.07563/) (2017)
- [Colorization as a Proxy Task for Visual Understanding](https://mlsanity.com/paper/1703.04044/) (2017)
- [Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark](https://mlsanity.com/paper/1704.03847/) (2017)
- [SPLATNet: Sparse Lattice Networks for Point Cloud Processing](https://mlsanity.com/paper/1802.08275/) (2018)
- [Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling](https://mlsanity.com/paper/1904.03375/) (2019)
- [ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics](https://mlsanity.com/paper/1908.06295/) (2019)
- [Multiresolution Tree Networks for 3D Point Cloud Processing](https://mlsanity.com/paper/1807.03520/) (2018)
- [Unsupervised Multi-Task Feature Learning on Point Clouds](https://mlsanity.com/paper/1910.08207/) (2019)
- [Recurrent Slice Networks for 3D Segmentation of Point Clouds](https://mlsanity.com/paper/1802.04402/) (2018)
- [How Useful is Self-Supervised Pretraining for Visual Tasks?](https://mlsanity.com/paper/2003.14323/) (2020)
- [Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds](https://mlsanity.com/paper/2003.13035/) (2020)
- [Fully-Convolutional Point Networks for Large-Scale Point Clouds](https://mlsanity.com/paper/1808.06840/) (2018)
- [Unsupervised Detection of Distinctive Regions on 3D Shapes](https://mlsanity.com/paper/1905.01684/) (2019)

## Built on by (most cited first, 27 of 27)

- [Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2308.11166/) (2023)
- [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://mlsanity.com/paper/2305.19812/) (2023)
- [2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision](https://mlsanity.com/paper/2310.12817/) (2023)
- [U3DS3: Unsupervised 3D Semantic Scene Segmentation](https://mlsanity.com/paper/2311.06018/) (2023)
- [BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation](https://mlsanity.com/paper/2308.06530/) (2023)
- [All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation](https://mlsanity.com/paper/2305.15832/) (2023)
- [CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2307.10316/) (2023)
- [3D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidance](https://mlsanity.com/paper/2407.09826/) (2024)
- [Centered Self-Attention Layers](https://mlsanity.com/paper/2306.01610/) (2023)
- [Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation](https://mlsanity.com/paper/2311.01989/) (2023)
- [You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation](https://mlsanity.com/paper/2304.11762/) (2023)
- [FreePoint: Unsupervised Point Cloud Instance Segmentation](https://mlsanity.com/paper/2305.06973/) (2023)
- [Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimization](https://mlsanity.com/paper/2401.06975/) (2024)
- [Subspace Prototype Guidance for Mitigating Class Imbalance in Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2408.10537/) (2024)
- [LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectives](https://mlsanity.com/paper/2503.18384/) (2025)
- [RealDriveSim: A Realistic Multi-Modal Multi-Task Synthetic Dataset for Autonomous Driving](https://mlsanity.com/paper/2506.16319/) (2025)
- [Partial Vessels Annotation-based Coronary Artery Segmentation with Self-training and Prototype Learning](https://mlsanity.com/paper/2307.04472/) (2023)
- [Weakly Supervised LiDAR Semantic Segmentation via Scatter Image Annotation](https://mlsanity.com/paper/2404.12861/) (2024)
- [Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2408.11280/) (2024)
- [Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2410.08091/) (2024)
- [Multi-modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation](https://mlsanity.com/paper/2312.16578/) (2023)
- [Towards Modality-agnostic Label-efficient Segmentation with Entropy-Regularized Distribution Alignment](https://mlsanity.com/paper/2408.16520/) (2024)
- [Bayesian Self-Training for Semi-Supervised 3D Segmentation](https://mlsanity.com/paper/2409.08102/) (2024)
- [High-quality Pseudo-labeling for Point Cloud Segmentation with Scene-level Annotation](https://mlsanity.com/paper/2506.23227/) (2025)
- [3D Weakly Supervised Semantic Segmentation via Class-Aware and Geometry-Guided Pseudo-Label Refinement](https://mlsanity.com/paper/2510.17875/) (2025)
- [You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding](https://mlsanity.com/paper/2303.14727/) (2023)
- [Weakly Supervised Point Cloud Segmentation via Conservative Propagation of Scene-level Labels](https://mlsanity.com/paper/2312.06799/) (2023)

## Abstract (arXiv)

Existing methods for large-scale point cloud semantic segmentation require expensive, tedious and error-prone manual point-wise annotations. Intuitively, weakly supervised training is a direct solution to reduce the cost of labeling. However, for weakly supervised large-scale point cloud semantic segmentation, too few annotations will inevitably lead to ineffective learning of network. We propose an effective weakly supervised method containing two components to solve the above problem. Firstly, we construct a pretext task, textiti.e., point cloud colorization, with a self-supervised learning to transfer the learned prior knowledge from a large amount of unlabeled point cloud to a weakly supervised network. In this way, the representation capability of the weakly supervised network can be improved by the guidance from a heterogeneous task. Besides, to generate pseudo label for unlabeled data, a sparse label propagation mechanism is proposed with the help of generated class prototypes, which is used to measure the classification confidence of unlabeled point. Our method is evaluated on large-scale point cloud datasets with different scenarios including indoor and outdoor. The experimental results show the large gain against existing weakly supervised and comparable results to fully supervised methodsfootnoteCode based on mindspore: https://github.com/dmcv-ecnu/MindSporeModelZoo/tree/main/WS3MindSpore.