Image Matching across Wide Baselines: From Paper to Practice

03/03/2020 ∙ by Yuhe Jin, et al. ∙ 36

We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task – the accuracy of the reconstructed camera pose – as our primary metric. Our pipeline's modular structure allows us to easily integrate, configure, and combine methods and heuristics. We demonstrate this by embedding dozens of popular algorithms and evaluating them, from seminal works to the cutting edge of machine learning research. We show that with proper settings, classical solutions may still outperform the perceived state of the art. Besides establishing the actual state of the art, the experiments conducted in this paper reveal unexpected properties of SfM pipelines that can be exploited to help improve their performance, for both algorithmic and learned methods. Data and code are online, providing an easy-to-use and flexible framework for the benchmarking of local feature and robust estimation methods, both alongside and against top-performing methods. This work provides the basis for an open challenge on wide-baseline image matching .



There are no comments yet.


page 1

page 3

page 5

page 8

page 13

page 14

page 18

page 19

Code Repositories


A general framework for map-based visual localization. It contains 1) Map Generation which support traditional features or deeplearning features. 2) Hierarchical-Localizationvisual in visual(points or line) map. 3)Fusion framework with IMU, wheel odom and GPS sensors.

view repo


The MAGSAC algorithm for robust model fitting without using an inlier-outlier threshold

view repo


Advanced RANSAC (DEGENSAC) with bells and whistles for H and F estimation

view repo


Fast and accurate python RANSAC with LO, LAF-check

view repo


MAGSAC: marginalizing sample consensus, python version

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.