Zobrazeno 1 - 10
of 240
pro vyhledávání: '"Rivera, Mariano"'
Recent Reference-Based image super-resolution (RefSR) has improved SOTA deep methods introducing attention mechanisms to enhance low-resolution images by transferring high-resolution textures from a reference high-resolution image. The main idea is t
Externí odkaz:
http://arxiv.org/abs/2310.01379
Autor:
Rivera, Mariano
Variational Autoencoders (VAEs) have become a cornerstone in generative modeling and representation learning within machine learning. This paper explores a nuanced aspect of VAEs, focusing on interpreting the Kullback-Leibler (KL) Divergence, a criti
Externí odkaz:
http://arxiv.org/abs/2309.13160
Autor:
Hoyos, Angello, Rivera, Mariano
We present a novel approach to enhance the capabilities of VQ-VAE models through the integration of a Residual Encoder and a Residual Pixel Attention layer, named Attentive Residual Encoder (AREN). The objective of our research is to improve the perf
Externí odkaz:
http://arxiv.org/abs/2309.11641
Autor:
Hoyos, Angello, Rivera, Mariano
The Hadamard Layer, a simple and computationally efficient way to improve results in semantic segmentation tasks, is presented. This layer has no free parameters that require to be trained. Therefore it does not increase the number of model parameter
Externí odkaz:
http://arxiv.org/abs/2302.10318
Autor:
Díaz Rivera, Mariano N., Amoruso, Lucía, Bocanegra, Yamile, Suárez, Jazmin X., Moreno, Leonardo, Muñoz, Edinson, Birba, Agustina, García, Adolfo M.
Publikováno v:
In Neurobiology of Aging April 2024 136:78-87
Autor:
Ehrlich, Hanna, Rivera, Mariano
We present a method for estimating intravoxel parameters from a DW-MRI based on deep learning techniques. We show that neural networks (DNNs) have the potential to extract information from diffusion-weighted signals to reconstruct cerebral tracts. We
Externí odkaz:
http://arxiv.org/abs/2103.11006
Autor:
Edoardo Flaviano, Silvia Bettinelli, Maddalena Assandri, Hassam Muhammad, Alberto Benigni, Gianluca Cappelleri, Edward Rivera Mariano, Luca Ferdinando Lorini, Dario Bugada
Publikováno v:
Korean Journal of Anesthesiology, Vol 76, Iss 4, Pp 326-335 (2023)
Background Ultrasound-guided supra-inguinal fascia iliaca block (FIB) provides effective analgesia after total hip arthroplasty (THA) but is complicated by high rates of motor block. The erector spinae plane block (ESPB) is a promising motor-sparing
Externí odkaz:
https://doaj.org/article/0f14c1d6c4c547939a1eb1798a59ebb7
Two steps phase shifting interferometry has been a hot topic in the recent years. We present a comparison study of 12 representative self--tunning algorithms based on two-steps phase shifting interferometry. We evaluate the performance of such algori
Externí odkaz:
http://arxiv.org/abs/2001.10101
Autor:
Reyes-Figueroa, Alan, Rivera, Mariano
We propose a new framework for processing Fringe Patterns (FP). Our novel approach builds upon the hypothesis that the denoising and normalisation of FPs can be learned by a deep neural network if enough pairs of corrupted and ideal FPs are provided.
Externí odkaz:
http://arxiv.org/abs/1906.06224
Autor:
Flores, Victor H., Rivera, Mariano
Publikováno v:
Optics Communications, Volume 461, 15 April 2020, 125286
We present the Simplified Lissajous Ellipse Fitting (SLEF) method for the calculation of the random phase step and the phase distribution from two phase-shifted interferograms. We consider interferograms with spatial and temporal dependency of backgr
Externí odkaz:
http://arxiv.org/abs/1904.05454