Deep Vanishing Point Detection

Deep Vanishing Point Detection: Geometric priors make dataset variations vanish

Lin, Y. (TU Delft Pattern Recognition and Bioinformatics)
Wiersma, R.T. (TU Delft Computer Graphics and Visualisation)
Pintea, S. (TU Delft Pattern Recognition and Bioinformatics)
Hildebrandt, K.A. (TU Delft Computer Graphics and Visualisation)
Eisemann, E. (TU Delft Computer Graphics and Visualisation)
van Gemert, J.C. (TU Delft Pattern Recognition and Bioinformatics)

O'Conner, L. (editor)

2022

Deep learning has improved vanishing point detection in images. Yet, deep networks require expensive annotated datasets trained on costly hardware and do not generalize to even slightly different domains, and minor problem variants. Here, we address these issues by injecting deep vanishing point detection networks with prior knowledge. This prior knowledge no longer needs to be learned from data, saving valuable annotation efforts and compute, unlocking realistic few-sample scenarios, and reducing the impact of domain changes. Moreover, the interpretability of the priors allows to adapt deep networks to minor problem variations such as switching between Manhattan and non-Manhattan worlds. We seamlessly incorporate two geometric priors: (i) Hough Transform -- mapping image pixels to straight lines, and (ii) Gaussian sphere -- mapping lines to great circles whose intersections denote vanishing points. Experimentally, we ablate our choices and show comparable accuracy to existing models in the large-data setting. We validate our model's improved data efficiency, robustness to domain changes, adaptability to non-Manhattan settings.

Hough transform
Vanishing point detection
Deep learning
Geometric priors

http://resolver.tudelft.nl/uuid:534d6977-ff59-443a-ab9d-4363a7a92bcb

https://doi.org/10.1109/CVPR52688.2022.00601

IEEE, Piscataway

2023-07-01

978-1-6654-6947-0

Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022-06-18 → 2022-06-24, New Orleans, United States

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1063-6919, 2022-June

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

conference paper

© 2022 Y. Lin, R.T. Wiersma, S. Pintea, K.A. Hildebrandt, E. Eisemann, J.C. van Gemert