Log In Sign Up

Image Matching across Wide Baselines: From Paper to Practice

by   Yuhe Jin, et al.

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 .


page 1

page 3

page 5

page 8

page 13

page 14

page 18

page 19


Guide Local Feature Matching by Overlap Estimation

Local image feature matching under large appearance, viewpoint, and dist...

Robust Image Retrieval-based Visual Localization using Kapture

In this paper, we present a versatile method for visual localization. It...

Rapid and robust endoscopic content area estimation: A lean GPU-based pipeline and curated benchmark dataset

Endoscopic content area refers to the informative area enclosed by the d...

FrOoDo: Framework for Out-of-Distribution Detection

FrOoDo is an easy-to-use and flexible framework for Out-of-Distribution ...

DeepFaceLab: A simple, flexible and extensible face swapping framework

DeepFaceLab is an open-source deepfake system created by iperov for face...

Standardized Evaluation of Machine Learning Methods for Evolving Data Streams

Due to the unspecified and dynamic nature of data streams, online machin...

DeepCAVE: An Interactive Analysis Tool for Automated Machine Learning

Automated Machine Learning (AutoML) is used more than ever before to sup...

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