A Data-efficient Framework for Robotics Large-scale LiDAR Scene Parsing
This work addresses a critical bottleneck in robotics for large-scale LiDAR scene parsing, enabling better representations for tasks like robotic manipulation and autonomous navigation with limited labeled data.
The paper tackles the problem of 3D point cloud understanding with limited labels by proposing a unified framework that uses unsupervised clustering, weak label-guided merging, and self-supervised optimization, achieving state-of-the-art performance in semantic segmentation, instance segmentation, and object detection under data-efficient settings.
Existing state-of-the-art 3D point clouds understanding methods only perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework which simultaneously solves the downstream high-level understanding tasks, especially when labels are extremely limited. This work presents a general and simple framework to tackle point clouds understanding when labels are limited. We propose a novel unsupervised region expansion based clustering method for generating clusters. More importantly, we innovatively propose to learn to merge the over-divided clusters based on the local low-level geometric property similarities and the learned high-level feature similarities supervised by weak labels. Hence, the true weak labels guide pseudo labels merging taking both geometric and semantic feature correlations into consideration. Finally, the self-supervised reconstruction and data augmentation optimization modules are proposed to guide the propagation of labels among semantically similar points within a scene. Experimental Results demonstrate that our framework has the best performance among the three most important weakly supervised point clouds understanding tasks including semantic segmentation, instance segmentation, and object detection even when limited points are labeled, under the data-efficient settings for the large-scale 3D semantic scene parsing. The developed techniques have postentials to be applied to downstream tasks for better representations in robotic manipulation and robotic autonomous navigation. Codes and models are publicly available at: https://github.com/KangchengLiu.