paper-with-me

홈 › Papers

On the Comparison of Classic and Deep Keypoint Detector and Descriptor Methods

2020-07-20 · Kristijan Bartol, David Bojanić, Tomislav Pribanić, Tomislav Petković, Yago Diez Donoso, Joaquim Salvi Mas

The purpose of this study is to give a performance comparison between several classic hand-crafted and deep key-point detector and descriptor methods. In particular, we consider the following classical algorithms: SIFT, SURF, ORB, FAST, BRISK, MSER, HARRIS, KAZE, AKAZE, AGAST, GFTT, FREAK, BRIEF and RootSIFT, where a subset of all combinations is paired into detector-descriptor pipelines. Additionally, we analyze the performance of two recent and perspective deep detector-descriptor models, LF-Net and SuperPoint. Our benchmark relies on the HPSequences dataset that provides real and diverse images under various geometric and illumination changes. We analyze the performance on three evaluation tasks: keypoint verification, image matching and keypoint retrieval. The results show that certain classic and deep approaches are still comparable, with some classic detector-descriptor combinations overperforming pretrained deep models. In terms of the execution times of tested implementations, SuperPoint model is the fastest, followed by ORB. The source code is published on \url{https://github.com/kristijanbartol/keypoint-algorithms-benchmark}.

📄 PDF Abstract BibTeX arXiv:2007.10000

Code (2)

kristijanbartol/hpatches-benchmark 공식 구현
kristijanbartol/keypoint-algorithms-benchmark 공식 구현

Tasks

Retrieval

Similar Papers 제목 키워드 기반

Comparing Feature Detectors: A bias in the repeatability criteria, and how to correct it

2014-09-08 · Ives Rey-Otero, Mauricio Delbracio, Jean-Michel Morel

Most computer vision application rely on algorithms finding local correspondences between different images. These algorithms detect and compare stable local invariant descriptors centered at scale-invariant keypoints. Be…

A Comparison of CNN and Classic Features for Image Retrieval

2019-08-25 · Umut Özaydın, Theodoros Georgiou, Michael Lew

Feature detectors and descriptors have been successfully used for various computer vision tasks, such as video object tracking and content-based image retrieval. Many methods use image gradients in different stages of th…

Content-Based Image RetrievalImage RetrievalKeypoint DetectionObject Tracking+2

R2D2: Reliable and Repeatable Detector and Descriptor

2019-12-01 · NeurIPS 2019 12 · Jerome Revaud, Cesar De Souza, Martin Humenberger, Philippe Weinzaepfel

Interest point detection and local feature description are fundamental steps in many computer vision applications. Classical approaches are based on a detect-then-describe paradigm where separate handcrafted methods are …

Atari GamesCamera LocalizationImage MatchingInterest Point Detection+2

Analysis of feature detector and descriptor combinations with a localization experiment for various performance metrics

2017-10-17 · Ertugrul Bayraktar, Pinar Boyraz

The purpose of this study is to provide a detailed performance comparison of feature detector/descriptor methods, particularly when their various combinations are used for image-matching. The localization experiments of …

R2D2: Repeatable and Reliable Detector and Descriptor

2019-06-14 · Jerome Revaud, Philippe Weinzaepfel, César De Souza, Noe Pion 외

Interest point detection and local feature description are fundamental steps in many computer vision applications. Classical methods for these tasks are based on a detect-then-describe paradigm where separate handcrafted…

Interest Point DetectionKeypoint DetectionMetric Learning