# Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenes

arXiv: https://arxiv.org/abs/2004.12498 · HTML: https://mlsanity.com/paper/2004.12498/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2020.

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

- [NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes](https://mlsanity.com/paper/2111.13260/) (2021)
- [One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation](https://mlsanity.com/paper/2104.02246/) (2021)
- [SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds](https://mlsanity.com/paper/2104.04891/) (2021)
- [Learning 3D Semantic Segmentation with only 2D Image Supervision](https://mlsanity.com/paper/2110.11325/) (2021)
- [LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds](https://mlsanity.com/paper/2210.08064/) (2022)
- [GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2305.16404/) (2023)
- [3D Spatial Recognition without Spatially Labeled 3D](https://mlsanity.com/paper/2105.06461/) (2021)
- [Interactive Object Segmentation in 3D Point Clouds](https://mlsanity.com/paper/2204.07183/) (2022)
- [Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2308.11166/) (2023)
- [LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation](https://mlsanity.com/paper/2211.05997/) (2022)
- [Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation](https://mlsanity.com/paper/2207.09084/) (2022)
- [PointDC:Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel Clustering](https://mlsanity.com/paper/2304.08965/) (2023)
- [Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision](https://mlsanity.com/paper/2201.02963/) (2022)
- [GaIA: Graphical Information Gain based Attention Network for Weakly Supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2210.01558/) (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)
- [Pointly-supervised 3D Scene Parsing with Viewpoint Bottleneck](https://mlsanity.com/paper/2109.08553/) (2021)
- [PointMatch: A Consistency Training Framework for Weakly Supervised Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2202.10705/) (2022)
- [Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation](https://mlsanity.com/paper/2311.01989/) (2023)
- [Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentation](https://mlsanity.com/paper/2303.05164/) (2023)
- [Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds](https://mlsanity.com/paper/2107.11267/) (2021)
- [Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervision](https://mlsanity.com/paper/2208.05110/) (2022)
- [Weakly Supervised 3D Instance Segmentation without Instance-level Annotations](https://mlsanity.com/paper/2308.01721/) (2023)
- [Weakly Supervised LiDAR Semantic Segmentation via Scatter Image Annotation](https://mlsanity.com/paper/2404.12861/) (2024)
- [Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignment](https://mlsanity.com/paper/2312.00663/) (2023)
- [Industrial3D: A Water-Treatment TLS Point Cloud Dataset and Cross-Paradigm Benchmark for MEP Scene Understanding](https://mlsanity.com/paper/2603.28660/) (2026)
- [You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding](https://mlsanity.com/paper/2303.14727/) (2023)
- [A Review and A Robust Framework of Data-Efficient 3D Scene Parsing with Traditional/Learned 3D Descriptors](https://mlsanity.com/paper/2312.01262/) (2023)

## Abstract (arXiv)

The deficiency of 3D segmentation labels is one of the main obstacles to effective point cloud segmentation, especially for scenes in the wild with varieties of different objects. To alleviate this issue, we propose a novel deep graph convolutional network-based framework for large-scale semantic scene segmentation in point clouds with sole 2D supervision. Different with numerous preceding multi-view supervised approaches focusing on single object point clouds, we argue that 2D supervision is capable of providing sufficient guidance information for training 3D semantic segmentation models of natural scene point clouds while not explicitly capturing their inherent structures, even with only single view per training sample. Specifically, a Graph-based Pyramid Feature Network (GPFN) is designed to implicitly infer both global and local features of point sets and an Observability Network (OBSNet) is introduced to further solve object occlusion problem caused by complicated spatial relations of objects in 3D scenes. During the projection process, perspective rendering and semantic fusion modules are proposed to provide refined 2D supervision signals for training along with a 2D-3D joint optimization strategy. Extensive experimental results demonstrate the effectiveness of our 2D supervised framework, which achieves comparable results with the state-of-the-art approaches trained with full 3D labels, for semantic point cloud segmentation on the popular SUNCG synthetic dataset and S3DIS real-world dataset.