# In the Saddle: Chasing Fast and Repeatable Features

arXiv: https://arxiv.org/abs/1608.06800 · HTML: https://mlsanity.com/paper/1608.06800/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2016.

## Built on by (most cited first, 2 of 2)

- [Learning and Crafting for the Wide Multiple Baseline Stereo](https://mlsanity.com/paper/2112.12027/) (2021)
- [Closed-loop Feedback Registration for Consecutive Images of Moving Flexible Targets](https://mlsanity.com/paper/2110.10772/) (2021)

## Abstract (arXiv)

A novel similarity-covariant feature detector that extracts points whose neighbourhoods, when treated as a 3D intensity surface, have a saddle-like intensity profile. The saddle condition is verified efficiently by intensity comparisons on two concentric rings that must have exactly two dark-to-bright and two bright-to-dark transitions satisfying certain geometric constraints. Experiments show that the Saddle features are general, evenly spread and appearing in high density in a range of images. The Saddle detector is among the fastest proposed. In comparison with detector with similar speed, the Saddle features show superior matching performance on number of challenging datasets.