Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation

arXiv:2403.10001v1 Announce Type: new
Abstract: Unsupervised domain adaptation (UDA) is vital for alleviating the workload of labeling 3D point cloud data and mitigating the absence of labels when facing a newly defined domain. Various methods of utilizing images to enhance the performance of cross-domain 3D segmentation have recently emerged. However, the pseudo labels, which are generated from models trained on the source domain and provide additional supervised signals for the unseen domain, are inadequate when utilized for 3D segmentation due …

abstract arxiv boost cloud cloud data cs.cv data domain domain adaptation foundation images labeling labels modal performance segmentation semantic type unsupervised visual vital