Current state-of-the-art point cloud-based perception methods usually rely on
large-scale labeled data, which requires expensive manual annotations. A
natural option is to explore the unsupervised methodology for 3D perception
tasks. However, such methods often face substantial performance-drop
difficulties. Fortunately, we found that there exist amounts of image-based
datasets and an alternative can be proposed, i.e., transferring the knowledge
in the 2D images to 3D point clouds. Specifically, we propose a novel approach
for the challenging cross-modal and cross-domain adaptation task by fully
exploring the relationship between images and point clouds and designing
effective feature alignment strategies. Without any 3D labels, our method
achieves state-of-the-art performance for 3D point cloud semantic segmentation
on SemanticKITTI by using the knowledge of KITTI360 and GTA5, compared to
existing unsupervised and weakly-supervised baselines.

通过探索图像和点云之间的关系并设计有效的特征对齐策略，我们提出了一种新颖的方法来解决具有挑战性的跨模态和跨域自适应任务，在没有任何 3D 标签的情况下，我们的方法利用 KITTI360 和 GTA5 的知识，在 SemanticKITTI 上达到了 3D 点云语义分割的最先进性能，相比现有的无监督和弱监督基准。