A Large Scale Homography Benchmark
Daniel Barath, Dmytro Mishkin, Michal Polic, Wolfgang F\"orstner, Jiri, Matas

TL;DR
This paper introduces Pi3D, a large-scale 3D plane dataset, and HEB, a comprehensive homography benchmark, enabling improved evaluation and training of geometric estimation algorithms under challenging conditions.
Contribution
It provides a new extensive dataset and benchmark for homography estimation, facilitating advances in robust geometric matching and deep learning methods.
Findings
Established state-of-the-art in robust homography estimation
Evaluated uncertainty in SIFT orientations and scales
Provided a large, diverse dataset for training and evaluation
Abstract
We present a large-scale dataset of Planes in 3D, Pi3D, of roughly 1000 planes observed in 10 000 images from the 1DSfM dataset, and HEB, a large-scale homography estimation benchmark leveraging Pi3D. The applications of the Pi3D dataset are diverse, e.g. training or evaluating monocular depth, surface normal estimation and image matching algorithms. The HEB dataset consists of 226 260 homographies and includes roughly 4M correspondences. The homographies link images that often undergo significant viewpoint and illumination changes. As applications of HEB, we perform a rigorous evaluation of a wide range of robust estimators and deep learning-based correspondence filtering methods, establishing the current state-of-the-art in robust homography estimation. We also evaluate the uncertainty of the SIFT orientations and scales w.r.t. the ground truth coming from the underlying homographies…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Vision and Imaging · Advanced Image and Video Retrieval Techniques · Robotics and Sensor-Based Localization
