B
Boris X. Vintimilla
Researcher at Escuela Superior Politecnica del Litoral
Publications - 60
Citations - 653
Boris X. Vintimilla is an academic researcher from Escuela Superior Politecnica del Litoral. The author has contributed to research in topics: Computer science & Channel (digital image). The author has an hindex of 11, co-authored 51 publications receiving 449 citations.
Papers
More filters
Proceedings ArticleDOI
Infrared Image Colorization Based on a Triplet DCGAN Architecture
TL;DR: A novel approach for colorizing near infrared (NIR) images using a Deep Convolutional Generative Adversarial Network (GAN) architecture based on the usage of a triplet model, which allows a fast convergence during the training, obtaining a greater similarity between the colored NIR image and the corresponding ground truth.
Journal ArticleDOI
Feature Point Descriptors: Infrared and Visible Spectra
Pablo Ricaurte,Carmen Chilán,Cristhian A. Aguilera-Carrasco,Boris X. Vintimilla,Angel D. Sappa +4 more
TL;DR: This manuscript evaluates the behavior of classical feature point descriptors when they are used in images from long-wave infrared spectral band and compare them with the results obtained in the visible spectrum.
Journal ArticleDOI
Wavelet-based visible and infrared image fusion: A comparative study
Angel D. Sappa,Juan A. Carvajal,Cristhian Aguilera,Miguel Oliveira,Dennis Romero,Boris X. Vintimilla +5 more
TL;DR: In this paper, the authors evaluated different wavelet-based cross-spectral image fusion strategies adopted to merge visible and infrared images in order to find correlations between setups and performance of obtained results, which can be used to define a criteria for selecting the best fusion strategy for a given pair of crossspectral images.
Book ChapterDOI
Learning to Colorize Infrared Images
TL;DR: This paper focuses on near infrared (NIR) image colorization by using a Generative Adversarial Network (GAN) architecture model, and a discriminative model is used to estimate the probability that the generated image came from the training dataset, rather than the image automatically generated.
Proceedings ArticleDOI
Thermal Image Super-resolution: A Novel Architecture and Dataset.
TL;DR: A novel CycleGAN architecture for thermal image super-resolution, together with a large dataset consisting of thermal images at different resolutions, based on ResNet6 as a Generator and PatchGAN as a Discriminator is proposed.