arXiv subjects

Alessandro Foi

Publications and source records attributed to Alessandro Foi.

5 recordsLinked to original sources

arXiv2025

BM4D-PC: nonlocal volumetric denoising of principal components of diffusion-weighted MR images

Purpose: Noise in diffusion-weighted MRI (dMRI) is often spatially correlated due to different acquisition and reconstruction strategies, which is not fully accounted for in current denoising strategies. Thus, we propose a novel model-based denoising method for dMRI that effectively accounts for the different noise characteristics of data. Methods: We propose a denoising strategy that incorporates full noise statistics, including the noise power spectral density (PSD), by leveraging the BM4D algorithm. Furthermore, to exploit redundancy across the diffusion MRI dataset, BM4D is applied to principal components (PC) of diffusion-weighted images (DWI) obtained through principal component analysis (PCA) decomposition of the entire DWI dataset, an approach we refer to as BM4D-PC. Importantly, our method also allows for direct estimation of both the noise map and PSD. We evaluated BM4D-PC against four existing state-of-the-art methods using in-silico and in vivo datasets, including high-resolution human and marmoset acquisitions. Results: Overall, BM4D-PC presented the best results for the metrics PSNR, SSIM and RMSE on the in-silico experiments. The in-vivo studies also showed that BM4D-PC dramatically enhanced the image quality of raw DWIs, outperforming existing denoising methods in terms of noise suppression and detail preservation, leading to improved quality of diffusion metrics. Conclusion: The proposed BM4D-PC method demonstrated state-of-the-art denoising results for dMRI using datasets from various acquisition strategies and image resolutions, potentially supporting future advances in neuroscience research.

eess.SP↗

arXiv2021

A feed-forward neural network as a nonlinear dynamics integrator for supercontinuum generation

The nonlinear propagation of ultrashort pulses in optical fiber depends sensitively on both input pulse and fiber parameters. As a result, optimizing propagation for specific applications generally requires time-consuming simulations based on sequential integration of the generalized nonlinear Schr\"odinger equation (GNLSE). Here, we train a feed-forward neural network to learn the differential propagation dynamics of the GNLSE, allowing emulation of direct numerical integration of fiber propagation, and particularly the highly complex case of supercontinuum generation. Comparison with a recurrent neural network shows that the feed-forward approach yields faster training and computation, and reduced memory requirements. The approach is generic and can be extended to other physical systems.

physics.comp-ph↗

arXiv2020

Object Pose Estimation in Robotics Revisited

Vision based object grasping and manipulation in robotics require accurate estimation of object's 6D pose. The 6D pose estimation has received significant attention in computer vision community and multiple datasets and evaluation metrics have been proposed. However, the existing metrics measure how well two geometrical surfaces are aligned - ground truth vs. estimated pose - which does not directly measure how well a robot can perform the task with the given estimate. In this work we propose a probabilistic metric that directly measures success in robotic tasks. The evaluation metric is based on non-parametric probability density that is estimated from samples of a real physical setup. During the pose evaluation stage the physical setup is not needed. The evaluation metric is validated in controlled experiments and a new pose estimation dataset of industrial parts is introduced. The experimental results with the parts confirm that the proposed evaluation metric better reflects the true performance in robotics than the existing metrics.

cs.CV↗

arXiv2020

Predicting ultrafast nonlinear dynamics in fibre optics with a recurrent neural network

The propagation of ultrashort pulses in optical fibre displays complex nonlinear dynamics that find important applications in fields such as high power pulse compression and broadband supercontinuum generation. Such nonlinear evolution however, depends sensitively on both the input pulse and fibre characteristics, and optimizing propagation for application purposes requires extensive numerical simulations based on generalizations of a nonlinear Schrödinger-type equation. This is computationally-demanding and creates a severe bottleneck in using numerical techniques to design and optimize experiments in real-time. Here, we present a solution to this problem using a machine-learning based paradigm to predict complex nonlinear propagation in optical fibres with a recurrent neural network, bypassing the need for direct numerical solution of a governing propagation model. Specifically, we show how a recurrent neural network with long short-term memory accurately predicts the temporal and spectral evolution of higher-order soliton compression and supercontinuum generation, solely from a given transform-limited input pulse intensity profile. Comparison with experiments for the case of soliton compression shows remarkable agreement in both temporal and spectral domains. In optics, our results apply readily to the optimization of pulse compression and broadband light sources, and more generally in physics, they open up new perspectives for studies in all nonlinear Schrödinger-type systems in studies of Bose-Einstein condensates, plasma physics, and hydrodynamics.

physics.optics↗

arXiv2018

Nonlocality-Reinforced Convolutional Neural Networks for Image Denoising

We introduce a paradigm for nonlocal sparsity reinforced deep convolutional neural network denoising. It is a combination of a local multiscale denoising by a convolutional neural network (CNN) based denoiser and a nonlocal denoising based on a nonlocal filter (NLF) exploiting the mutual similarities between groups of patches. CNN models are leveraged with noise levels that progressively decrease at every iteration of our framework, while their output is regularized by a nonlocal prior implicit within the NLF. Unlike complicated neural networks that embed the nonlocality prior within the layers of the network, our framework is modular, it uses standard pre-trained CNNs together with standard nonlocal filters. An instance of the proposed framework, called NN3D, is evaluated over large grayscale image datasets showing state-of-the-art performance.

eess.IV↗