RT Conference Proceedings
T1 Homography estimation with deep convolutional neural networks by random color transformations
A1 Molina-Cabello, Miguel Ángel
A1 Elizondo Acuña, David Alberto
A1 Luque-Baena, Rafael Marcos
A1 López-Rubio, Ezequiel
K1 Redes neuronales
AB Most classic approaches to homography estimation are based on the filtering of outliers by means of the RANSAC method. New proposals include deep convolutional neural networks. Here a new method for homography estimation is presented, which supplies a deep neural homography estimator with color perturbated versions of the original image pair. The obtained outputs are combined in order to obtain a more robust estimation of the underlying homography. Experimental results are shown, which demonstrate the adequate performance of our approach, both in quantitative and qualitative terms.
YR 2019
FD 2019-09-13
LK https://hdl.handle.net/10630/18345
UL https://hdl.handle.net/10630/18345
LA eng
NO Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 27 feb 2026