Paper ID: 2406.09126

Auto-Vocabulary Segmentation for LiDAR Points

Weijie Wei, Osman Ülger, Fatemeh Karimi Nejadasl, Theo Gevers, Martin R. Oswald

Existing perception methods for autonomous driving fall short of recognizing unknown entities not covered in the training data. Open-vocabulary methods offer promising capabilities in detecting any object but are limited by user-specified queries representing target classes. We propose AutoVoc3D, a framework for automatic object class recognition and open-ended segmentation. Evaluation on nuScenes showcases AutoVoc3D's ability to generate precise semantic classes and accurate point-wise segmentation. Moreover, we introduce Text-Point Semantic Similarity, a new metric to assess the semantic similarity between text and point cloud without eliminating novel classes.

Submitted: Jun 13, 2024