# Multi-View Projection for Unsupervised Domain Adaptation in 3D Semantic Segmentation

arXiv: https://arxiv.org/abs/2505.15545 · HTML: https://mlsanity.com/paper/2505.15545/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 24 of 24)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud](https://mlsanity.com/paper/1809.08495/) (2018)
- [SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks](https://mlsanity.com/paper/1609.05130/) (2016)
- [MSeg: A Composite Dataset for Multi-domain Semantic Segmentation](https://mlsanity.com/paper/2112.13762/) (2021)
- [Neural Kernel Surface Reconstruction](https://mlsanity.com/paper/2305.19590/) (2023)
- [Virtual Multi-view Fusion for 3D Semantic Segmentation](https://mlsanity.com/paper/2007.13138/) (2020)
- [Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation](https://mlsanity.com/paper/2107.05399/) (2021)
- [Learning 3D Semantic Segmentation with only 2D Image Supervision](https://mlsanity.com/paper/2110.11325/) (2021)
- [Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation](https://mlsanity.com/paper/2204.07548/) (2022)
- [Multi-View Deep Learning for Consistent Semantic Mapping with RGB-D Cameras](https://mlsanity.com/paper/1703.08866/) (2017)
- [UniMix: Towards Domain Adaptive and Generalizable LiDAR Semantic Segmentation in Adverse Weather](https://mlsanity.com/paper/2404.05145/) (2024)
- [SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation](https://mlsanity.com/paper/2304.03251/) (2023)
- [Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation](https://mlsanity.com/paper/2308.14619/) (2023)
- [LiDAR-UDA: Self-ensembling Through Time for Unsupervised LiDAR Domain Adaptation](https://mlsanity.com/paper/2309.13523/) (2023)
- [LDLS: 3-D Object Segmentation Through Label Diffusion From 2-D Images](https://mlsanity.com/paper/1910.13955/) (2019)
- [Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domains](https://mlsanity.com/paper/2312.12098/) (2023)
- [T-UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Clouds](https://mlsanity.com/paper/2309.08302/) (2023)
- [3D Can Be Explored In 2D: Pseudo-Label Generation for LiDAR Point Clouds Using Sensor-Intensity-Based 2D Semantic Segmentation](https://mlsanity.com/paper/2505.03300/) (2025)

## Abstract (arXiv)

3D semantic segmentation plays a pivotal role in autonomous driving and road infrastructure analysis, yet state-of-the-art 3D models are prone to severe domain shift when deployed across different datasets. In this paper, we propose an Unsupervised Domain Adaptation approach where a 3D segmentation model is trained on the target dataset using pseudo-labels generated by a novel multi-view projection framework. Our approach first aligns Lidar scans into coherent 3D scenes and renders them from multiple virtual camera poses to create large-scale synthetic 2D semantic segmentation datasets in various modalities. The generated datasets are used to train an ensemble of 2D segmentation models in point cloud view domain on each modality. During inference, the models process a large amount of views per scene; the resulting logits are back-projected to 3D with a depth-aware voting scheme to generate final point-wise labels. These labels are then used to fine-tune a 3D segmentation model in the target domain. We evaluate our approach Real-to-Real on the nuScenes and SemanticKITTI datasets. We also evaluate it Simulation-to-Real with the SynLidar dataset. Our contributions are a novel method that achieves state-of-the-art results in Real-to-Real Unsupervised Domain Adaptation, and we also demonstrate an application of our method to segment rare classes, for which target 3D annotations are not available, by only using 2D annotations for those classes and leveraging 3D annotations for other classes in a source domain.