Recurrence-based Vanishing Point Detection
This addresses the problem of vanishing point detection for computer vision applications by offering an unsupervised alternative that avoids the need for labeled datasets, though it is incremental in combining existing ideas.
The paper tackles vanishing point detection by proposing an unsupervised method that uses both explicit and implicit lines from recurring correspondences, outperforming classical and supervised deep learning methods on synthetic images and matching supervised approaches on real-world images.
Classical approaches to Vanishing Point Detection (VPD) rely solely on the presence of explicit straight lines in images, while recent supervised deep learning approaches need labeled datasets for training. We propose an alternative unsupervised approach: Recurrence-based Vanishing Point Detection (R-VPD) that uses implicit lines discovered from recurring correspondences in addition to explicit lines. Furthermore, we contribute two Recurring-Pattern-for-Vanishing-Point (RPVP) datasets: 1) a Synthetic Image dataset with 3,200 ground truth vanishing points and camera parameters, and 2) a Real-World Image dataset with 1,400 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.