Handcrafted outlier detection revisited
(2020) 16th European Conference on Computer Vision, ECCV 2020 In Lecture Notes in Computer Science 12364. p.770-787- Abstract
- Local feature matching is a critical part of many computer vision pipelines, including among others Structure-from-Motion, SLAM, and Visual Localization. However, due to limitations in the descriptors, raw matches are often contaminated by a majority of outliers. As a result, outlier detection is a fundamental problem in computer vision and a wide range of approaches, from simple checks based on descriptor similarity to geometric verification, have been proposed over the last decades. In recent years, deep learning-based approaches to outlier detection have become popular. Unfortunately, the corresponding works rarely compare with strong classical baselines. In this paper we revisit handcrafted approaches to outlier filtering. Based on... (More)
- Local feature matching is a critical part of many computer vision pipelines, including among others Structure-from-Motion, SLAM, and Visual Localization. However, due to limitations in the descriptors, raw matches are often contaminated by a majority of outliers. As a result, outlier detection is a fundamental problem in computer vision and a wide range of approaches, from simple checks based on descriptor similarity to geometric verification, have been proposed over the last decades. In recent years, deep learning-based approaches to outlier detection have become popular. Unfortunately, the corresponding works rarely compare with strong classical baselines. In this paper we revisit handcrafted approaches to outlier filtering. Based on best practices, we propose a hierarchical pipeline for effective outlier detection as well as integrate novel ideas which in sum lead to an efficient and competitive approach to outlier rejection. We show that our approach, although not relying on learning, is more than competitive to both recent learned works as well as handcrafted approaches, both in terms of efficiency and effectiveness. The code is available at https://github.com/cavalli1234/AdaLAM. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/30cd0a3e-6b30-4f7d-a3dc-b931bada0a3a
- author
- Cavalli, Luca ; Larsson, Viktor LU ; Oswald, Martin Ralf ; Sattler, Torsten and Pollefeys, Marc
- publishing date
- 2020
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Computer Vision – ECCV 2020 : 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIX - 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIX
- series title
- Lecture Notes in Computer Science
- volume
- 12364
- pages
- 18 pages
- publisher
- Springer
- conference name
- 16th European Conference on Computer Vision, ECCV 2020
- conference location
- Glasgow, United Kingdom
- conference dates
- 2020-08-23 - 2020-08-28
- external identifiers
-
- scopus:85097276469
- ISSN
- 1611-3349
- 0302-9743
- ISBN
- 978-3-030-58529-7
- 978-3-030-58528-0
- DOI
- 10.1007/978-3-030-58529-7_45
- language
- English
- LU publication?
- no
- id
- 30cd0a3e-6b30-4f7d-a3dc-b931bada0a3a
- date added to LUP
- 2022-09-06 13:16:19
- date last changed
- 2024-06-27 20:24:37
@inproceedings{30cd0a3e-6b30-4f7d-a3dc-b931bada0a3a,
abstract = {{Local feature matching is a critical part of many computer vision pipelines, including among others Structure-from-Motion, SLAM, and Visual Localization. However, due to limitations in the descriptors, raw matches are often contaminated by a majority of outliers. As a result, outlier detection is a fundamental problem in computer vision and a wide range of approaches, from simple checks based on descriptor similarity to geometric verification, have been proposed over the last decades. In recent years, deep learning-based approaches to outlier detection have become popular. Unfortunately, the corresponding works rarely compare with strong classical baselines. In this paper we revisit handcrafted approaches to outlier filtering. Based on best practices, we propose a hierarchical pipeline for effective outlier detection as well as integrate novel ideas which in sum lead to an efficient and competitive approach to outlier rejection. We show that our approach, although not relying on learning, is more than competitive to both recent learned works as well as handcrafted approaches, both in terms of efficiency and effectiveness. The code is available at https://github.com/cavalli1234/AdaLAM.}},
author = {{Cavalli, Luca and Larsson, Viktor and Oswald, Martin Ralf and Sattler, Torsten and Pollefeys, Marc}},
booktitle = {{Computer Vision – ECCV 2020 : 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIX}},
isbn = {{978-3-030-58529-7}},
issn = {{1611-3349}},
language = {{eng}},
pages = {{770--787}},
publisher = {{Springer}},
series = {{Lecture Notes in Computer Science}},
title = {{Handcrafted outlier detection revisited}},
url = {{http://dx.doi.org/10.1007/978-3-030-58529-7_45}},
doi = {{10.1007/978-3-030-58529-7_45}},
volume = {{12364}},
year = {{2020}},
}