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

arXiv: https://arxiv.org/abs/2007.10000 · HTML: https://mlsanity.com/paper/2007.10000/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2020.

## Built on by (most cited first, 5 of 5)

- [Stereo Visual Odometry with Deep Learning-Based Point and Line Feature Matching using an Attention Graph Neural Network](https://mlsanity.com/paper/2308.01125/) (2023)
- [Classic versus deep learning approaches to address computer vision challenges](https://mlsanity.com/paper/2101.09744/) (2021)
- [Deep Learning-Based UAV Aerial Triangulation without Image Control Points](https://mlsanity.com/paper/2301.02869/) (2023)
- [A Survey of Feature detection methods for localisation of plain sections of Axial Brain Magnetic Resonance Imaging](https://mlsanity.com/paper/2302.04173/) (2023)
- [PySIFT: GPU-Resident Deterministic SIFT for Deep Learning Vision Pipelines](https://mlsanity.com/paper/2605.17869/) (2026)

## Abstract (arXiv)

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 urlhttps://github.com/kristijanbartol/keypoint-algorithms-benchmark.