Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction
This work addresses a domain-specific problem in computer vision for applications like smartphone-based imaging, offering incremental improvements in accuracy with a rough prior.
The paper tackles the problem of estimating orthogonal vanishing points and camera focal length in uncalibrated images using a prior gravity direction, achieving superior accuracy compared to state-of-the-art methods with comparable runtimes.
We tackle the problem of estimating a Manhattan frame, i.e. three orthogonal vanishing points, and the unknown focal length of the camera, leveraging a prior vertical direction. The direction can come from an Inertial Measurement Unit that is a standard component of recent consumer devices, e.g., smartphones. We provide an exhaustive analysis of minimal line configurations and derive two new 2-line solvers, one of which does not suffer from singularities affecting existing solvers. Additionally, we design a new non-minimal method, running on an arbitrary number of lines, to boost the performance in local optimization. Combining all solvers in a hybrid robust estimator, our method achieves increased accuracy even with a rough prior. Experiments on synthetic and real-world datasets demonstrate the superior accuracy of our method compared to the state of the art, while having comparable runtimes. We further demonstrate the applicability of our solvers for relative rotation estimation. The code is available at https://github.com/cvg/VP-Estimation-with-Prior-Gravity.