Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation (ECCV 2022)
Authors: Runyu Ding*, Jihan Yang*, Li Jiang, Xiaojuan Qi (* equal contribution)
In this work, we propose a Data-Oriented Domain Adaptation (DODA) framework on sim-to-real domain adaptation for 3D indoor semantic segmentation. Our empirical studies demonstrate two unique challengeds in this setting: the point pattern gap and the context gap caused by different sensing mechanisms and layout placements across domains. Thus, we propose virtual scan simulation to imitate real-world point cloud patterns and tail-aware cuboid mixing to alleviate the interior context gap with a cuboid-based intermediate domain. The first unsupervised sim-to-real adaptation benchmark on 3D indoor semantic segmentation is also built on 3D-FRONT, ScanNet and S3DIS along with 8 popular UDA methods.
Please refer to INSTALL.md for the installation.
Please refer to GETTING_STARTED.md to learn more usage.
- Release code
- Support pre-trained model
- Support other baseline methods
| method | mIoU | download |
|---|---|---|
| DODA (only VSS) | 40.52 | model |
| DODA | 51.33 | model |
| method | mIoU | download |
|---|---|---|
| DODA (only VSS) | 47.18 | model |
| DODA | 56.54 | model |
Notice that
- DODA performance relies on the pretrain model (DODA (only VSS)). If you find the self-training performance is unsatisfactory, consider to re-train a better pretrain model.
- Performance on 3D-FRONT
$\rightarrow$ S3DIS is quite unstable with high standard variance due to its simplicity and small sample sizes.
Our code base is partially borrowed from PointGroup, PointWeb and OpenPCDet.
If you find this project useful in your research, please consider cite:
@inproceedings{ding2022doda,
title={DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation},
author={Ding, Runyu and Yang, Jihan and Jiang, Li and Qi, Xiaojuan},
booktitle={ECCV},
year={2022}
}