1 code implementation • 7 Apr 2022 • Anguelos Nicolaou, Vincent Christlein, Edgar Riba, Jian Shi, Georg Vogeler, Mathias Seuret
We propose the use of fractals as a means of efficient data augmentation.
Ranked #1 on No real Data Binarization on DIBCO and H_DIBCO 2009
1 code implementation • 19 Nov 2020 • Jian Shi, Edgar Riba, Dmytro Mishkin, Francesc Moreno, Anguelos Nicolaou
In this paper we present a review of the Kornia differentiable data augmentation (DDA) module for both for spatial (2D) and volumetric (3D) tensors.
4 code implementations • 5 Oct 2019 • Edgar Riba, Dmytro Mishkin, Daniel Ponsa, Ethan Rublee, Gary Bradski
This work presents Kornia -- an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems.
4 code implementations • 4 Sep 2019 • Xavier Soria, Edgar Riba, Angel D. Sappa
This dataset has been used for training the proposed approach as well the state-of-the-art algorithms for comparisons.
Ranked #1 on Edge Detection on CID
3 code implementations • ICCV 2019 • Axel Barroso-Laguna, Edgar Riba, Daniel Ponsa, Krystian Mikolajczyk
We introduce a novel approach for keypoint detection task that combines handcrafted and learned CNN filters within a shallow multi-scale architecture.
Ranked #5 on Image Matching on IMC PhotoTourism (using extra training data)