-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yuan_2024_CVPR, author = {Yuan, Zhimin and Zeng, Wankang and Su, Yanfei and Liu, Weiquan and Cheng, Ming and Guo, Yulan and Wang, Cheng}, title = {Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23303-23312} }
Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds
Abstract
3D synthetic-to-real unsupervised domain adaptive segmentation is crucial to annotating new domains. Self-training is a competitive approach for this task but its performance is limited by different sensor sampling patterns (i.e. variations in point density) and incomplete training strategies. In this work we propose a density-guided translator (DGT) which translates point density between domains and integrates it into a two-stage self-training pipeline named DGT-ST. First in contrast to existing works that simultaneously conduct data generation and feature/output alignment within unstable adversarial training we employ the non-learnable DGT to bridge the domain gap at the input level. Second to provide a well-initialized model for self-training we propose a category-level adversarial network in stage one that utilizes the prototype to prevent negative transfer. Finally by leveraging the designs above a domain-mixed self-training method with source-aware consistency loss is proposed in stage two to narrow the domain gap further. Experiments on two synthetic-to-real segmentation tasks (SynLiDAR ? semanticKITTI and SynLiDAR ? semanticPOSS) demonstrate that DGT-ST outperforms state-of-the-art methods achieving 9.4% and 4.3% mIoU improvements respectively. Code is available at https://github.com/yuan-zm/DGT-ST.
Related Material