From CAD Models to Soft Point Cloud Labels: An Automatic Annotation Pipeline for Cheaply Supervised 3D Semantic Segmentation

Research output: Contribution to journalJournal articleResearchpeer-review

1 Citation (Scopus)
56 Downloads (Pure)

Abstract

We propose a fully automatic annotation scheme that takes a raw 3D point cloud with a set of fitted CAD models as input and outputs convincing point-wise labels that can be used as cheap training data for point cloud segmentation. Compared with manual annotations, we show that our automatic labels are accurate while drastically reducing the annotation time and eliminating the need for manual intervention or dataset-specific parameters. Our labeling pipeline outputs semantic classes and soft point-wise object scores, which can either be binarized into standard one-hot-encoded labels, thresholded into weak labels with ambiguous points left unlabeled, or used directly as soft labels during training. We evaluate the label quality and segmentation performance of PointNet++ on a dataset of real industrial point clouds and Scan2CAD, a public dataset of indoor scenes. Our results indicate that reducing supervision in areas that are more difficult to label automatically is beneficial compared with the conventional approach of naively assigning a hard “best guess” label to every point.
Original languageEnglish
Article number3578
JournalRemote Sensing
Volume15
Issue number14
ISSN2072-4292
DOIs
Publication statusPublished - Jul 2023

Keywords

  • 3D semantic segmentation
  • automatic labeling
  • deep learning
  • point clouds
  • soft labels

Fingerprint

Dive into the research topics of 'From CAD Models to Soft Point Cloud Labels: An Automatic Annotation Pipeline for Cheaply Supervised 3D Semantic Segmentation'. Together they form a unique fingerprint.

Cite this