Search Results for author:
Found 30 papers, 9 papers with code
Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution
Diffusion models have revolutionized image synthesis, garnering significant research interest in recent years.
Adversarial Deep-Unfolding Network for MA-XRF Super-Resolution on Old Master Paintings Using Minimal Training Data
Numerical results demonstrate that our method outperforms existing state-of-the-art super-resolution techniques for MA-XRF scans of Old Master paintings.
Reconstructing classes of 3D FRI signals from sampled tomographic projections at unknown angles
By using the divergence theorem, we are able to retrieve the projected vertices of the polyhedron from the sampled tomographic projections, and then we show how to retrieve the 3D object and the projection angles from this information.
Enhanced Event-Based Video Reconstruction with Motion Compensation
To address this, we propose warping the input intensity frames and sparse codes to enhance reconstruction quality.
CommIN: Semantic Image Communications as an Inverse Problem with INN-Guided Diffusion Models
In this work, we propose CommIN, which views the recovery of high-quality source images from degraded reconstructions as an inverse problem.
First-spike coding promotes accurate and efficient spiking neural networks for discrete events with rich temporal structures
In the backpropagation, we develop an error assignment method that propagates error from FS times to spikes through a Gaussian window, and then supervised learning for spikes is implemented through a surrogate gradient approach.
INDigo: An INN-Guided Probabilistic Diffusion Algorithm for Inverse Problems
With the help of INN, our algorithm effectively estimates the details lost in the degradation process and is no longer limited by the requirement of knowing the closed-form expression of the degradation model.
Sensing Diversity and Sparsity Models for Event Generation and Video Reconstruction from Events
In this paper, we propose a light, simple model-based deep network for E2V reconstruction, explore the diversity for adjacent pixels in V2E generation, and finally build a video-to-events-to-video (V2E2V) architecture to validate how alternative event generation strategies improve video reconstruction.
Learning-Based Reconstruction of FRI Signals
While the deep unfolded network achieves similar performance as the classical FRI techniques and outperforms the encoder-decoder network in the low noise regimes, the latter allows to reconstruct the FRI signal even when the sampling kernel is unknown.
Generative Joint Source-Channel Coding for Semantic Image Transmission
In GenerativeJSCC, we carry out end-to-end training of an encoder and a StyleGAN-based decoder, and show that GenerativeJSCC significantly outperforms DeepJSCC both in terms of distortion and perceptual quality.
A Fast Automatic Method for Deconvoluting Macro X-ray Fluorescence Data Collected from Easel Paintings
Macro X-ray Fluorescence (MA-XRF) scanning is increasingly widely used by researchers in heritage science to analyse easel paintings as one of a suite of non-invasive imaging techniques.
DURRNet: Deep Unfolded Single Image Reflection Removal Network
With the deep unrolling technique, we build the DURRNet with ProxNets to model natural image priors and ProxInvNets which are constructed with invertible networks to impose the exclusion prior.
Active Privacy-Utility Trade-off Against Inference in Time-Series Data Sharing
For privacy measure, we consider both the probability of correctly detecting the true value of the secret and the mutual information (MI) between the secret and the released data.
Mixed X-Ray Image Separation for Artworks with Concealed Designs
In this paper, we focus on X-ray images of paintings with concealed sub-surface designs (e. g., deriving from reuse of the painting support or revision of a composition by the artist), which include contributions from both the surface painting and the concealed features.
AI-based Reconstruction for Fast MRI -- A Systematic Review and Meta-analysis
Compressed sensing (CS) has been playing a key role in accelerating the magnetic resonance imaging (MRI) acquisition process.
Light-Field Microscopy for optical imaging of neuronal activity: when model-based methods meet data-driven approaches
This paper is devoted to a comprehensive survey to state-of-the-art of computational methods for LFM, with a focus on model-based and data-driven approaches.
Privacy-Aware Communication Over a Wiretap Channel with Generative Networks
We study privacy-aware communication over a wiretap channel using end-to-end learning.
WINNet: Wavelet-inspired Invertible Network for Image Denoising
The proposed WINNet consists of K-scale of lifting inspired invertible neural networks (LINNs) and sparsity-driven denoising networks together with a noise estimation network.
LINN: Lifting Inspired Invertible Neural Network for Image Denoising
In this paper, we propose an invertible neural network for image denoising (DnINN) inspired by the transform-based denoising framework.
Model-inspired Deep Learning for Light-Field Microscopy with Application to Neuron Localization
Light-field microscopes are able to capture spatial and angular information of incident light rays.
Active Privacy-utility Trade-off Against a Hypothesis Testing Adversary
We consider a user releasing her data containing some personal information in return of a service.
Privacy-Aware Time-Series Data Sharing with Deep Reinforcement Learning
We measure the privacy leakage by the mutual information between the user's true data sequence and shared version.
Learning Deep Analysis Dictionaries for Image Super-Resolution
Inspired by the recent success of deep neural networks and the recent efforts to develop multi-layer dictionary models, we propose a Deep Analysis dictionary Model (DeepAM) which is optimized to address a specific regression task known as single image super-resolution.
Learning Deep Analysis Dictionaries -- Part II: Convolutional Dictionaries
By exploiting the properties of a convolutional dictionary, we present an efficient convolutional analysis dictionary learning approach.
Wavelet Domain Style Transfer for an Effective Perception-distortion Tradeoff in Single Image Super-Resolution
In this paper, we propose a novel method based on wavelet domain style transfer (WDST), which achieves a better PD tradeoff than the GAN based methods.
Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusion
In this paper, we propose a novel deep convolutional neural network to solve the general multi-modal image restoration (MIR) and multi-modal image fusion (MIF) problems.
Privacy-Aware Location Sharing with Deep Reinforcement Learning
Existing approaches are mainly focused on privacy of sharing a single location or myopic location trace privacy; neither of them taking into account the temporal correlations between the past and current locations.
Information Theory Cryptography and Security Information Theory
Reconstructing Classes of Non-bandlimited Signals from Time Encoded Information
We investigate time encoding as an alternative method to classical sampling, and address the problem of reconstructing non-bandlimited signals from time-based samples.
Signal Processing
Multimodal Image Super-resolution via Joint Sparse Representations induced by Coupled Dictionaries
This paper proposes a new approach to construct a high-resolution (HR) version of a low-resolution (LR) image given another HR image modality as reference, based on joint sparse representations induced by coupled dictionaries.
Deep De-Aliasing for Fast Compressive Sensing MRI
Fast Magnetic Resonance Imaging (MRI) is highly in demand for many clinical applications in order to reduce the scanning cost and improve the patient experience.
