Fast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces

By Pablo Fernández Alcantarilla, Jesús Nuevo, Adrien Bartoli. British Machine Vision Conference, 2013

1,253 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b05568c6467d716b93fc98fdf345dafdcb1ef617

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. José M. M. Montiel
2. Krystian Mikolajczyk
3. Juan D. Tardós
4. Zahra Saleem
5. Shaharyar Ahmed Khan Tareen
6. Edgar Riba
7. Raul Mur-Artal
8. Junjun Jiang

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Jiayi Ma
3. Andrea Vedaldi
4. Dacheng Tao
5. Andrew Zisserman
6. Trevor Darrell
7. Jitendra Malik
8. Pascal Fua

Citations in the corpus

• Pose Estimation for Augmented Reality: A Hands-On Survey (2016, neutral): “more robust, and accelerated for real-time detection [3].”
• ORB-SLAM: A Versatile and Accurate Monocular SLAM System (2015, methodology): “We require features that need for extraction much less than 33 ms per image, which excludes the popular SIFT (∼ 300 ms) [19], SURF (∼ 300 ms) [18], or the recent A-KAZE (∼ 100 ms) [35].”
• Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “An accelerated version called AKAZA (Alcantarilla and Solutions 2011) is implemented by embedding the fast explicit diffusion in a pyramidal framework to dramatically speedup feature detection in nonlinear scale spaces.”
• Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters (2019, methodology): “Multi-scale improvements were proposed in KAZE [21] and its extension, A-KAZE [22], where Hessian detector was applied to a non-linear diffusion scale space in contrast to widely used Gaussian pyramid.”
• A comparative analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK (2018, methodology): “In this article, SIFT (blobs) [13], SURF (blobs) [14], KAZE (blobs) [15], AKAZE (blobs) [16], ORB (corners) [17], and BRISK (corners) [18] algorithms are compared for image matching and registration.”
• OpenMVG: Open Multiple View Geometry (2016, background): “The current implementation allows to detect and describe: • Blob regions (Scale invariant points): SIFT [11] (based on VlFeat [20] and Sift Anatomy [12]), AKAZE [22].”
• LF-Net: Learning Local Features from Images (2018, methodology): “They are versatile [2, 2, 4] and remain useful in many scenarios.”