# Synthetic-to-Real Domain Generalized Semantic Segmentation for 3D Indoor Point Clouds

arXiv: https://arxiv.org/abs/2212.04668 · HTML: https://mlsanity.com/paper/2212.04668/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 45 references that are in the map.
- First posted on arXiv 9 Dec 2022.

## Builds on (most cited first, 30 of 33)

- [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)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics](https://mlsanity.com/paper/2011.09127/) (2020)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016)
- [Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data](https://mlsanity.com/paper/1909.00889/) (2019)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [DACS: Domain Adaptation via Cross-domain Mixed Sampling](https://mlsanity.com/paper/2007.08702/) (2020)
- [RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening](https://mlsanity.com/paper/2103.15597/) (2021)
- [ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning](https://mlsanity.com/paper/2007.07936/) (2020)
- [ParseNet: Looking Wider to See Better](https://mlsanity.com/paper/1506.04579/) (2015)
- [FSDR: Frequency Space Domain Randomization for Domain Generalization](https://mlsanity.com/paper/2103.02370/) (2021)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [Mix3D: Out-of-Context Data Augmentation for 3D Scenes](https://mlsanity.com/paper/2110.02210/) (2021)
- [ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape](https://mlsanity.com/paper/1812.02781/) (2018)
- [Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification](https://mlsanity.com/paper/2012.00417/) (2020)
- [Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2204.02548/) (2022)
- [Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2110.08188/) (2021)
- [Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2006.12052/) (2020)
- [Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation](https://mlsanity.com/paper/2207.04892/) (2022)
- [SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network](https://mlsanity.com/paper/2104.07861/) (2021)

## Built on by (most cited first, 8 of 8)

- [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://mlsanity.com/paper/2305.19812/) (2023)
- [DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding](https://mlsanity.com/paper/2407.08801/) (2024)
- [AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring](https://mlsanity.com/paper/2501.09428/) (2025)
- [How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation](https://mlsanity.com/paper/2505.18956/) (2025)
- [CCF: Complementary Collaborative Fusion for Domain Generalized Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2603.23276/) (2026)
- [Domain Expansion and Boundary Growth for Open-Set Single-Source Domain Generalization](https://mlsanity.com/paper/2411.02920/) (2024)
- [Dual-supervised Asymmetric Co-training for Semi-supervised Medical Domain Generalization](https://mlsanity.com/paper/2509.20785/) (2025)
- [ModelNet40-E: An Uncertainty-Aware Benchmark for Point Cloud Classification](https://mlsanity.com/paper/2508.01269/) (2025)

## Abstract (arXiv)

Semantic segmentation in 3D indoor scenes has achieved remarkable performance under the supervision of large-scale annotated data. However, previous works rely on the assumption that the training and testing data are of the same distribution, which may suffer from performance degradation when evaluated on the out-of-distribution scenes. To alleviate the annotation cost and the performance degradation, this paper introduces the synthetic-to-real domain generalization setting to this task. Specifically, the domain gap between synthetic and real-world point cloud data mainly lies in the different layouts and point patterns. To address these problems, we first propose a clustering instance mix (CINMix) augmentation technique to diversify the layouts of the source data. In addition, we augment the point patterns of the source data and introduce non-parametric multi-prototypes to ameliorate the intra-class variance enlarged by the augmented point patterns. The multi-prototypes can model the intra-class variance and rectify the global classifier in both training and inference stages. Experiments on the synthetic-to-real benchmark demonstrate that both CINMix and multi-prototypes can narrow the distribution gap and thus improve the generalization ability on real-world datasets.