%0 Conference Proceedings
%T Transfer Learning from Synthetic Data in the Camera Pose Estimation Problem
%A Jorge Charco
%A Angel Sappa
%A Boris X. Vintimilla
%A Henry Velesaca
%B 15th International Conference on Computer Vision Theory and Applications
%D 2020
%F Jorge Charco2020
%O MSIAU; 600.130; 601.349; 600.122
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3433), last updated on Tue, 25 Apr 2023 14:04:25 +0200
%X This paper presents a novel Siamese network architecture, as a variant of Resnet-50, to estimate the relative camera pose on multi-view environments. In order to improve the performance of the proposed model a transfer learning strategy, based on synthetic images obtained from a virtual-world, is considered. The transfer learning consists of first training the network using pairs of images from the virtual-world scenarioconsidering different conditions (i.e., weather, illumination, objects, buildings, etc.); then, the learned weightof the network are transferred to the real case, where images from real-world scenarios are considered. Experimental results and comparisons with the state of the art show both, improvements on the relative pose estimation accuracy using the proposed model, as well as further improvements when the transfer learning strategy (synthetic-world data transfer learning real-world data) is considered to tackle the limitation on thetraining due to the reduced number of pairs of real-images on most of the public data sets.
%U http://refbase.cvc.uab.es/files/CSV2020.pdf
%U http://dx.doi.org/10.5220/0009167604980505