Recurrence-Based Vanishing Point Detection

Skanda Bharadwaj, Robert T. Collins, Yanxi Liu; Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 2025, pp. 8909-8918

Classical approaches to Vanishing Point Detection (VPD) rely solely on the presence of explicit straight lines in images. Recent supervised deep learning methods rely on learned filters from labeled datasets. We propose an alternative unsupervised approach: Recurrence-based Vanishing Point Detection (R-VPD) that uses implicit lines derived from discovered recurring correspondences in addition to explicit lines. Furthermore we contribute two new VPD datasets: 1) a Synthetic Image dataset with 3200 ground truth vanishing points and 2) a Real-World Image dataset with 1400 human annotated vanishing points. We compare our method with two classical methods and two state-of-the-art deep learning-based VPD methods. We demonstrate that our unsupervised approach outperforms all the methods on the synthetic images dataset outperforms the classical methods and is on par with the supervised learning approaches on real-world images. Code and data can be found here: http://vision.cse.psu.edu/data/data.shtml