177 citations · 608 across the 34 of their papers we have counts for
40 papers
Scalable neural pushbroom architectures for real-time denoising of hyperspectral images onboard satellites
Ziyao Yi, Davide Piccinini, Diego Valsesia +2
The next generation of Earth observation satellites will seek to deploy intelligent models directly onboard the payload in order to minimize the latency incurred by the transmissio…
A low-complexity method for efficient depth-guided image deblurring
Ziyao Yi, Diego Valsesia, Tiziano Bianchi +1
Image deblurring is a challenging problem in imaging due to its highly ill-posed nature. Deep learning models have shown great success in tackling this problem but the quest for th…
A novel method and dataset for depth-guided image deblurring from smartphone Lidar
Antonio Montanaro, Diego Valsesia
Modern smartphones are equipped with Lidar sensors providing depth-sensing capabilities. Recent works have shown that this complementary sensor allows to improve various tasks in i…
Compress-Align-Detect: onboard change detection from unregistered images
Gabriele Inzerillo, Diego Valsesia, Aniello Fiengo +1
Change detection from satellite images typically incurs a delay ranging from several hours up to days because of latency in downlinking the acquired images and generating orthorect…
Onboard Hyperspectral Super-Resolution with Deep Pushbroom Neural Network
Davide Piccinini, Diego Valsesia, Enrico Magli
Hyperspectral imagers on satellites obtain the fine spectral signatures essential for distinguishing one material from another at the expense of limited spatial resolution. Enhanci…
Deep Lidar-guided Image Deblurring
Ziyao Yi, Diego Valsesia, Tiziano Bianchi +1
The rise of portable Lidar instruments, including their adoption in smartphones, opens the door to novel computational imaging techniques. Being an active sensing instrument, Lidar…
DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching
Emanuele Aiello, Umberto Michieli, Diego Valsesia +2
Personalized image generation requires text-to-image generative models that capture the core features of a reference subject to allow for controlled generation across different con…
Efficient onboard multi-task AI architecture based on self-supervised learning
Gabriele Inzerillo, Diego Valsesia, Enrico Magli
There is growing interest towards the use of AI directly onboard satellites for quick analysis and rapid response to critical events such as natural disasters. This paper presents…
MotionCraft: Physics-based Zero-Shot Video Generation
Luca Savant Aira, Antonio Montanaro, Emanuele Aiello +2
Generating videos with realistic and physically plausible motion is one of the main recent challenges in computer vision. While diffusion models are achieving compelling results in…
Modeling uncertainty for Gaussian Splatting
Luca Savant, Diego Valsesia, Enrico Magli
We present Stochastic Gaussian Splatting (SGS): the first framework for uncertainty estimation using Gaussian Splatting (GS). GS recently advanced the novel-view synthesis field by…
Onboard deep lossless and near-lossless predictive coding of hyperspectral images with line-based attention
Diego Valsesia, Tiziano Bianchi, Enrico Magli
Deep learning methods have traditionally been difficult to apply to compression of hyperspectral images onboard of spacecrafts, due to the large computational complexity needed to…
Deep 3D World Models for Multi-Image Super-Resolution Beyond Optical Flow
Luca Savant Aira, Diego Valsesia, Andrea Bordone Molini +3
Multi-image super-resolution (MISR) allows to increase the spatial resolution of a low-resolution (LR) acquisition by combining multiple images carrying complementary information i…
Fast Inference in Denoising Diffusion Models via MMD Finetuning
Emanuele Aiello, Diego Valsesia, Enrico Magli
Denoising Diffusion Models (DDMs) have become a popular tool for generating high-quality samples from complex data distributions. These models are able to capture sophisticated pat…
Rethinking the compositionality of point clouds through regularization in the hyperbolic space
Antonio Montanaro, Diego Valsesia, Enrico Magli
Point clouds of 3D objects exhibit an inherent compositional nature where simple parts can be assembled into progressively more complex shapes to form whole objects. Explicitly cap…
Cross-modal Learning for Image-Guided Point Cloud Shape Completion
Emanuele Aiello, Diego Valsesia, Enrico Magli
In this paper we explore the recent topic of point cloud completion, guided by an auxiliary image. We show how it is possible to effectively combine the information from the two mo…
Exploring the solution space of linear inverse problems with GAN latent geometry
Antonio Montanaro, Diego Valsesia, Enrico Magli
Inverse problems consist in reconstructing signals from incomplete sets of measurements and their performance is highly dependent on the quality of the prior knowledge encoded via…
Super-resolved multi-temporal segmentation with deep permutation-invariant networks
Diego Valsesia, Enrico Magli
Multi-image super-resolution from multi-temporal satellite acquisitions of a scene has recently enjoyed great success thanks to new deep learning models. In this paper, we go beyon…
Semi-supervised learning for joint SAR and multispectral land cover classification
Antonio Montanaro, Diego Valsesia, Giulia Fracastoro +1
Semi-supervised learning techniques are gaining popularity due to their capability of building models that are effective, even when scarce amounts of labeled data are available. In…
Permutation invariance and uncertainty in multitemporal image super-resolution
Diego Valsesia, Enrico Magli
Recent advances have shown how deep neural networks can be extremely effective at super-resolving remote sensing imagery, starting from a multitemporal collection of low-resolution…
Denoise and Contrast for Category Agnostic Shape Completion
Antonio Alliegro, Diego Valsesia, Giulia Fracastoro +2
In this paper, we present a deep learning model that exploits the power of self-supervision to perform 3D point cloud completion, estimating the missing part and a context region a…
RAN-GNNs: breaking the capacity limits of graph neural networks
Diego Valsesia, Giulia Fracastoro, Enrico Magli
Graph neural networks have become a staple in problems addressing learning and analysis of data defined over graphs. However, several results suggest an inherent difficulty in extr…
Deep Learning Methods For Synthetic Aperture Radar Image Despeckling: An Overview Of Trends And Perspectives
Giulia Fracastoro, Enrico Magli, Giovanni Poggi +3
Synthetic aperture radar (SAR) images are affected by a spatially-correlated and signal-dependent noise called speckle, which is very severe and may hinder image exploitation. Desp…
Learning Graph-Convolutional Representations for Point Cloud Denoising
Francesca Pistilli, Giulia Fracastoro, Diego Valsesia +1
Point clouds are an increasingly relevant data type but they are often corrupted by noise. We propose a deep neural network based on graph-convolutional layers that can elegantly d…
Speckle2Void: Deep Self-Supervised SAR Despeckling with Blind-Spot Convolutional Neural Networks
Andrea Bordone Molini, Diego Valsesia, Giulia Fracastoro +1
Information extraction from synthetic aperture radar (SAR) images is heavily impaired by speckle noise, hence despeckling is a crucial preliminary step in scene analysis algorithms…