Abstract

teaser.png

We propose an unsupervised method for parsing large 3D scans of real-world scenes into interpretable parts. Our goal is to provide a practical tool for analyzing 3D scenes with unique characteristics in the context of aerial surveying and mapping, without relying on application- specific user annotations. Our approach is based on a probabilistic reconstruction model that decomposes an input 3D point cloud into a small set of learned prototypical shapes. Our model provides an interpretable reconstruction of complex scenes and leads to relevant instance and semantic segmentations. To demonstrate the usefulness of our results, we introduce a novel dataset of seven diverse aerial LiDAR scans. We show that our method outperforms state-of-the-art unsupervised methods in terms of decom- position accuracy while remaining visually interpretable. Our method offers significant advantage over existing approaches, as it does not require any manual annotations, making it a practical and efficient tool for 3D scene analysis.

The Earth Parser Dataset - A new dataset to train and evaluate parsing methods on large, uncurated aerial LiDAR scans

earthparserdataset

Dataset overview.
Dataset ToolboxDownload DatasetCodePaperPoster

Learnable Earth Parser - An unsupervised method for parsing large 3D scans of real-world scenes into interpretable parts

learnableearthparser

Pipeline overview.

Citation

If you find this project useful for your research, please cite:

@misc{loiseau2023learnable,
      title={Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans}, 
      author={Romain Loiseau and Elliot Vincent and Mathieu Aubry and Loic Landrieu},
      year={2023},
      eprint={2304.09704},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
Dataset ToolboxDownload DatasetCodePaperPoster

Acknowledgements

This work was supported in part by ANR project READY3D ANR-19-CE23-0007 and was granted access to the HPC resources of IDRIS under the allocation 2022-AD011012096R2 made by GENCI. The work of MA was partly supported by the European Research Council (ERC project DISCOVER, number 101076028). The scenes of the Earth Parser Dataset were acquired and annotated by the LiDAR-HD project. We thank Zenodo for hosting the dataset. We thank Zeynep Sonat Baltaci, Nicolas Dufour, Antoine Gu├ędon, Helen Mair Rawsthorne, Tom Monnier, Damien Robert, Mathis Petrovich and Yannis Siglidis for inspiring discussions and valuable feedback.