# A Unified Point-Based Framework for 3D Segmentation

arXiv: https://arxiv.org/abs/1908.00478 · HTML: https://mlsanity.com/paper/1908.00478/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2019.

## Built on by (most cited first, 30 of 34)

- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [Stratified Transformer for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2203.14508/) (2022)
- [Sonata: Self-Supervised Learning of Reliable Point Representations](https://mlsanity.com/paper/2503.16429/) (2025)
- [OctFormer: Octree-based Transformers for 3D Point Clouds](https://mlsanity.com/paper/2305.03045/) (2023)
- [Fast Point Transformer](https://mlsanity.com/paper/2112.04702/) (2021)
- [Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training](https://mlsanity.com/paper/2308.09718/) (2023)
- [Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy](https://mlsanity.com/paper/2403.06467/) (2024)
- [Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation](https://mlsanity.com/paper/2204.07548/) (2022)
- [Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2107.14724/) (2021)
- [Learning from 2D: Contrastive Pixel-to-Point Knowledge Transfer for 3D Pretraining](https://mlsanity.com/paper/2104.04687/) (2021)
- [Deep Learning Based 3D Segmentation: A Survey](https://mlsanity.com/paper/2103.05423/) (2021)
- [PointConvFormer: Revenge of the Point-based Convolution](https://mlsanity.com/paper/2208.02879/) (2022)
- [Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization](https://mlsanity.com/paper/2207.11209/) (2022)
- [ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding](https://mlsanity.com/paper/2312.11112/) (2023)
- [LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels](https://mlsanity.com/paper/2403.15173/) (2024)
- [Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation](https://mlsanity.com/paper/2311.01989/) (2023)
- [Language-Assisted 3D Feature Learning for Semantic Scene Understanding](https://mlsanity.com/paper/2211.14091/) (2022)
- [Continual Road-Scene Semantic Segmentation via Feature-Aligned Symmetric Multi-Modal Network](https://mlsanity.com/paper/2308.04702/) (2023)
- [Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2308.09314/) (2023)
- [Full Point Encoding for Local Feature Aggregation in 3D Point Clouds](https://mlsanity.com/paper/2303.04458/) (2023)
- [SignX: Continuous Sign Recognition in Compact Pose-Rich Latent Space](https://mlsanity.com/paper/2504.16315/) (2025)
- [Similarity-Aware Fusion Network for 3D Semantic Segmentation](https://mlsanity.com/paper/2107.01579/) (2021)
- [Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation](https://mlsanity.com/paper/2212.06682/) (2022)
- [VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation](https://mlsanity.com/paper/2107.13824/) (2021)
- [BelHouse3D: A Benchmark Dataset for Assessing Occlusion Robustness in 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2411.13251/) (2024)
- [HexPlane Representation for 3D Semantic Scene Understanding](https://mlsanity.com/paper/2503.05127/) (2025)
- [Pixels-to-Graph: Real-time Integration of Building Information Models and Scene Graphs for Semantic-Geometric Human-Robot Understanding](https://mlsanity.com/paper/2506.22593/) (2025)
- [RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings](https://mlsanity.com/paper/2605.10706/) (2026)
- [Long Range Pooling for 3D Large-Scale Scene Understanding](https://mlsanity.com/paper/2301.06962/) (2023)

## Abstract (arXiv)

3D point cloud segmentation remains challenging for structureless and textureless regions. We present a new unified point-based framework for 3D point cloud segmentation that effectively optimizes pixel-level features, geometrical structures and global context priors of an entire scene. By back-projecting 2D image features into 3D coordinates, our network learns 2D textural appearance and 3D structural features in a unified framework. In addition, we investigate a global context prior to obtain a better prediction. We evaluate our framework on ScanNet online benchmark and show that our method outperforms several state-of-the-art approaches. We explore synthesizing camera poses in 3D reconstructed scenes for achieving higher performance. In-depth analysis on feature combinations and synthetic camera pose verify that features from different modalities benefit each other and dense camera pose sampling further improves the segmentation results.