Image Matching across Wide Baselines: From Paper to Practice
Preprint
Abstract
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 easy integration, configuration, and combination of different methods and heuristics. This is demonstrated 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 conducted experiments reveal unexpected properties of Structure from Motion (SfM) pipelines that can help improve their performance, for both algorithmic and learned methods. Data and code are online https://github.com/vcg-uvic/image-matching-benchmark, providing an easy-to-use and flexible framework for the benchmarking of local features and robust estimation methods, both alongside and against top-performing methods. This work provides a basis for the Image Matching Challenge https://vision.uvic.ca/image-matching-challenge.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Is There Anything New to Say About SIFT Matching?International Journal of Computer Vision, 2020
- Image Search with Selective Match Kernels: Aggregation Across Single and Multiple ImagesInternational Journal of Computer Vision, 2015
- Interesting Interest PointsInternational Journal of Computer Vision, 2011
- Automatic Panoramic Image Stitching using Invariant FeaturesInternational Journal of Computer Vision, 2006
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Multiple View Geometry in Computer Vision2004
- MLESAC: A New Robust Estimator with Application to Estimating Image GeometryComputer Vision and Image Understanding, 2000
- In defense of the eight-point algorithmIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- Projective reconstruction and invariants from multiple imagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994
- Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography1987