arXiv subjects

Pier Luigi Dragotti

Publications and source records attributed to Pier Luigi Dragotti.

At least 19 recordsLinked to original sources

arXiv2026

On the Anisotropy of Score-Based Generative Models

We investigate the role of network architecture in shaping the inductive biases of modern score-based generative models. To this end, we introduce the Score Anisotropy Directions (SADs), architecture-dependent directions that reveal how different networks preferentially capture data structure. Our analysis suggests that SADs form adaptive bases aligned with the architecture's output geometry, providing a principled way to predict generalization ability in score models prior to training. Through both synthetic data and standard image benchmarks, we demonstrate that SADs reliably capture fine-grained model behavior and correlate with downstream performance, as measured by Wasserstein metrics. Our work offers a new lens for explaining and predicting directional biases of generative models.

cs.LG↗

arXiv2026

CycleULM: A unified label-free deep learning framework for ultrasound localisation microscopy

Super-resolution ultrasound via microbubble (MB) localisation and tracking, also known as ultrasound localisation microscopy (ULM), can resolve microvasculature beyond the acoustic diffraction limit. However, significant challenges remain in localisation performance and data acquisition and processing time. Deep learning methods for ULM have shown promise to address these challenges, however, they remain limited by in vivo label scarcity and the simulation-to-reality domain gap. We present CycleULM, the first unified label-free deep learning framework for ULM. CycleULM learns a physics-emulating translation between the real contrast-enhanced ultrasound (CEUS) data domain and a simplified MB-only domain, leveraging the power of CycleGAN without requiring paired ground truth data. With this translation, CycleULM removes dependence on high-fidelity simulators or labelled data, and makes MB localisation and tracking substantially easier. Deployed as modular plug-and-play components within existing pipelines or as an end-to-end processing framework, CycleULM delivers substantial performance gains across both in silico and in vivo datasets. Specifically, CycleULM improves image contrast (contrast-to-noise ratio) by up to 15.3 dB and sharpens CEUS resolution with a 2.5{\times} reduction in the full width at half maximum of the point spread function. CycleULM also improves MB localisation performance, with up to +40% recall, +46% precision, and a -14.0 μm mean localisation error, yielding more faithful vascular reconstructions. Importantly, CycleULM achieves real-time processing throughput at 18.3 frames per second with order-of-magnitude speed-ups (up to ~14.5{\times}). By combining label-free learning, performance enhancement, and computational efficiency, CycleULM provides a practical pathway toward robust, real-time ULM and accelerates its translation to clinical applications.

eess.IV↗

arXiv2025

Leveraging Overfitting for Low-Complexity and Modality-Agnostic Joint Source-Channel Coding

This paper introduces Implicit-JSCC, a novel overfitted joint source-channel coding paradigm that directly optimizes channel symbols and a lightweight neural decoder for each source. This instance-specific strategy eliminates the need for training datasets or pre-trained models, enabling a storage-free, modality-agnostic solution. As a low-complexity alternative, Implicit-JSCC achieves efficient image transmission with around 1000x lower decoding complexity, using as few as 607 model parameters and 641 multiplications per pixel. This overfitted design inherently addresses source generalizability and achieves state-of-the-art results in the high SNR regimes, underscoring its promise for future communication systems, especially streaming scenarios where one-time offline encoding supports multiple online decoding.

eess.IV↗

arXiv2025

Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution

Diffusion models have transformed image synthesis through iterative denoising, by defining trajectories from noise to coherent data. While their capabilities are widely celebrated, a critical challenge remains unaddressed: ensuring responsible use by verifying whether an image originates from a model's training set, its novel generations or external sources. We introduce a framework that analyzes diffusion trajectories for this purpose. Specifically, we demonstrate that temporal dynamics across the entire trajectory allow for more robust classification and challenge the widely-adopted "Goldilocks zone" conjecture, which posits that membership inference is effective only within narrow denoising stages. More fundamentally, we expose critical flaws in current membership inference practices by showing that representative methods fail under distribution shifts or when model-generated data is present. For model attribution, we demonstrate a first white-box approach directly applicable to diffusion. Ultimately, we propose the unification of data provenance into a single, cohesive framework tailored to modern generative systems.

cs.CV↗

arXiv2025

LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression

We introduce and validate the lottery codec hypothesis, which states that untrained subnetworks within randomly initialized networks can serve as synthesis networks for overfitted image compression, achieving rate-distortion (RD) performance comparable to trained networks. This hypothesis leads to a new paradigm for image compression by encoding image statistics into the network substructure. Building on this hypothesis, we propose LotteryCodec, which overfits a binary mask to an individual image, leveraging an over-parameterized and randomly initialized network shared by the encoder and the decoder. To address over-parameterization challenges and streamline subnetwork search, we develop a rewind modulation mechanism that improves the RD performance. LotteryCodec outperforms VTM and sets a new state-of-the-art in single-image compression. LotteryCodec also enables adaptive decoding complexity through adjustable mask ratios, offering flexible compression solutions for diverse device constraints and application requirements.

eess.IV↗

arXiv2025

LatentINDIGO: An INN-Guided Latent Diffusion Algorithm for Image Restoration

There is a growing interest in the use of latent diffusion models (LDMs) for image restoration (IR) tasks due to their ability to model effectively the distribution of natural images. While significant progress has been made, there are still key challenges that need to be addressed. First, many approaches depend on a predefined degradation operator, making them ill-suited for complex or unknown degradations that deviate from standard analytical models. Second, many methods struggle to provide a stable guidance in the latent space and finally most methods convert latent representations back to the pixel domain for guidance at every sampling iteration, which significantly increases computational and memory overhead. To overcome these limitations, we introduce a wavelet-inspired invertible neural network (INN) that simulates degradations through a forward transform and reconstructs lost details via the inverse transform. We further integrate this design into a latent diffusion pipeline through two proposed approaches: LatentINDIGO-PixelINN, which operates in the pixel domain, and LatentINDIGO-LatentINN, which stays fully in the latent space to reduce complexity. Both approaches alternate between updating intermediate latent variables under the guidance of our INN and refining the INN forward model to handle unknown degradations. In addition, a regularization step preserves the proximity of latent variables to the natural image manifold. Experiments demonstrate that our algorithm achieves state-of-the-art performance on synthetic and real-world low-quality images, and can be readily adapted to arbitrary output sizes.

cs.CV↗

arXiv2025

Trustworthy Image Super-Resolution via Generative Pseudoinverse

We consider the problem of trustworthy image restoration, taking the form of a constrained optimization over the prior density. To this end, we develop generative models for the task of image super-resolution that respect the degradation process and that can be made asymptotically consistent with the low-resolution measurements, outperforming existing methods by a large margin in that respect.

eess.IV↗

arXiv2025

SING: Semantic Image Communications using Null-Space and INN-Guided Diffusion Models

Joint source-channel coding systems based on deep neural networks (DeepJSCC) have recently demonstrated remarkable performance in wireless image transmission. Existing methods primarily focus on minimizing distortion between the transmitted image and the reconstructed version at the receiver, often overlooking perceptual quality. This can lead to severe perceptual degradation when transmitting images under extreme conditions, such as low bandwidth compression ratios (BCRs) and low signal-to-noise ratios (SNRs). In this work, we propose SING, a novel two-stage JSCC framework that formulates the recovery of high-quality source images from corrupted reconstructions as an inverse problem. Depending on the availability of information about the DeepJSCC encoder/decoder and the channel at the receiver, SING can either approximate the stochastic degradation as a linear transformation, or leverage invertible neural networks (INNs) for precise modeling. Both approaches enable the seamless integration of diffusion models into the reconstruction process, enhancing perceptual quality. Experimental results demonstrate that SING outperforms DeepJSCC and other approaches, delivering superior perceptual quality even under extremely challenging conditions, including scenarios with significant distribution mismatches between the training and test data.

eess.IV↗

arXiv2025

SMILENet: Unleashing Extra-Large Capacity Image Steganography via a Synergistic Mosaic InvertibLE Hiding Network

Existing image steganography methods face fundamental limitations in hiding capacity (typically $1\sim7$ images) due to severe information interference and uncoordinated capacity-distortion trade-off. We propose SMILENet, a novel synergistic framework that achieves 25 image hiding through three key innovations: (i) A synergistic network architecture coordinates reversible and non-reversible operations to efficiently exploit information redundancy in both secret and cover images. The reversible Invertible Cover-Driven Mosaic (ICDM) module and Invertible Mosaic Secret Embedding (IMSE) module establish cover-guided mosaic transformations and representation embedding with mathematically guaranteed invertibility for distortion-free embedding. The non-reversible Secret Information Selection (SIS) module and Secret Detail Enhancement (SDE) module implement learnable feature modulation for critical information selection and enhancement. (ii) A unified training strategy that coordinates complementary modules to achieve 3.0x higher capacity than existing methods with superior visual quality. (iii) Last but not least, we introduce a new metric to model Capacity-Distortion Trade-off for evaluating the image steganography algorithms that jointly considers hiding capacity and distortion, and provides a unified evaluation approach for accessing results with different number of secret image. Extensive experiments on DIV2K, Paris StreetView and ImageNet1K show that SMILENet outperforms state-of-the-art methods in terms of hiding capacity, recovery quality as well as security against steganalysis methods.

cs.CV↗

arXiv2025

A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removal

Single Image Reflection Removal (SIRR) is a canonical blind source separation problem and refers to the issue of separating a reflection-contaminated image into a transmission and a reflection image. The core challenge lies in minimizing the commonalities among different sources. Existing deep learning approaches either neglect the significance of feature interactions or rely on heuristically designed architectures. In this paper, we propose a novel Deep Exclusion unfolding Network (DExNet), a lightweight, interpretable, and effective network architecture for SIRR. DExNet is principally constructed by unfolding and parameterizing a simple iterative Sparse and Auxiliary Feature Update (i-SAFU) algorithm, which is specifically designed to solve a new model-based SIRR optimization formulation incorporating a general exclusion prior. This general exclusion prior enables the unfolded SAFU module to inherently identify and penalize commonalities between the transmission and reflection features, ensuring more accurate separation. The principled design of DExNet not only enhances its interpretability but also significantly improves its performance. Comprehensive experiments on four benchmark datasets demonstrate that DExNet achieves state-of-the-art visual and quantitative results while utilizing only approximately 8\% of the parameters required by leading methods.

eess.IV↗

arXiv2025

INDIGO+: A Unified INN-Guided Probabilistic Diffusion Algorithm for Blind and Non-Blind Image Restoration

Generative diffusion models are becoming one of the most popular prior in image restoration (IR) tasks due to their remarkable ability to generate realistic natural images. Despite achieving satisfactory results, IR methods based on diffusion models present several limitations. First of all, most non-blind approaches require an analytical expression of the degradation model to guide the sampling process. Secondly, most existing blind approaches rely on families of pre-defined degradation models for training their deep networks. The above issues limit the flexibility of these approaches and so their ability to handle real-world degradation tasks. In this paper, we propose a novel INN-guided probabilistic diffusion algorithm for non-blind and blind image restoration, namely INDIGO and BlindINDIGO, which combines the merits of the perfect reconstruction property of invertible neural networks (INN) with the strong generative capabilities of pre-trained diffusion models. Specifically, we train the forward process of the INN to simulate an arbitrary degradation process and use the inverse to obtain an intermediate image that we use to guide the reverse diffusion sampling process through a gradient step. We also introduce an initialization strategy, to further improve the performance and inference speed of our algorithm. Experiments demonstrate that our algorithm obtains competitive results compared with recently leading methods both quantitatively and visually on synthetic and real-world low-quality images.

cs.CV↗

arXiv2024

Adversarial Deep-Unfolding Network for MA-XRF Super-Resolution on Old Master Paintings Using Minimal Training Data

High-quality element distribution maps enable precise analysis of the material composition and condition of Old Master paintings. These maps are typically produced from data acquired through Macro X-ray fluorescence (MA-XRF) scanning, a non-invasive technique that collects spectral information. However, MA-XRF is often limited by a trade-off between acquisition time and resolution. Achieving higher resolution requires longer scanning times, which can be impractical for detailed analysis of large artworks. Super-resolution MA-XRF provides an alternative solution by enhancing the quality of MA-XRF scans while reducing the need for extended scanning sessions. This paper introduces a tailored super-resolution approach to improve MA-XRF analysis of Old Master paintings. Our method proposes a novel adversarial neural network architecture for MA-XRF, inspired by the Learned Iterative Shrinkage-Thresholding Algorithm. It is specifically designed to work in an unsupervised manner, making efficient use of the limited available data. This design avoids the need for extensive datasets or pre-trained networks, allowing it to be trained using just a single high-resolution RGB image alongside low-resolution MA-XRF data. Numerical results demonstrate that our method outperforms existing state-of-the-art super-resolution techniques for MA-XRF scans of Old Master paintings.

eess.IV↗

arXiv2024

Reconstructing classes of 3D FRI signals from sampled tomographic projections at unknown angles

Traditional sampling schemes often assume that the sampling locations are known. Motivated by the recent bioimaging technique known as cryogenic electron microscopy (cryoEM), we consider the problem of reconstructing an unknown 3D structure from samples of its 2D tomographic projections at unknown angles. We focus on 3D convex bilevel polyhedra and 3D point sources and show that the exact estimation of these 3D structures and of the projection angles can be achieved up to an orthogonal transformation. Moreover, we are able to show that the minimum number of projections needed to achieve perfect reconstruction is independent of the complexity of the signal model. 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. The proof of our theorem is constructive and leads to a robust reconstruction algorithm, which we validate under various conditions. Finally, we apply aspects of the proposed framework to calibration of X-ray computed tomography (CT) data.

eess.SP↗

arXiv2024

Enhanced Event-Based Video Reconstruction with Motion Compensation

Deep neural networks for event-based video reconstruction often suffer from a lack of interpretability and have high memory demands. A lightweight network called CISTA-LSTC has recently been introduced showing that high-quality reconstruction can be achieved through the systematic design of its architecture. However, its modelling assumption that input signals and output reconstructed frame share the same sparse representation neglects the displacement caused by motion. To address this, we propose warping the input intensity frames and sparse codes to enhance reconstruction quality. A CISTA-Flow network is constructed by integrating a flow network with CISTA-LSTC for motion compensation. The system relies solely on events, in which predicted flow aids in reconstruction and then reconstructed frames are used to facilitate flow estimation. We also introduce an iterative training framework for this combined system. Results demonstrate that our approach achieves state-of-the-art reconstruction accuracy and simultaneously provides reliable dense flow estimation. Furthermore, our model exhibits flexibility in that it can integrate different flow networks, suggesting its potential for further performance enhancement.

cs.CV↗

arXiv2023

CommIN: Semantic Image Communications as an Inverse Problem with INN-Guided Diffusion Models

Joint source-channel coding schemes based on deep neural networks (DeepJSCC) have recently achieved remarkable performance for wireless image transmission. However, these methods usually focus only on the distortion of the reconstructed signal at the receiver side with respect to the source at the transmitter side, rather than the perceptual quality of the reconstruction which carries more semantic information. As a result, severe perceptual distortion can be introduced under extreme conditions such as low bandwidth and low signal-to-noise ratio. In this work, we propose CommIN, which views the recovery of high-quality source images from degraded reconstructions as an inverse problem. To address this, CommIN combines Invertible Neural Networks (INN) with diffusion models, aiming for superior perceptual quality. Through experiments, we show that our CommIN significantly improves the perceptual quality compared to DeepJSCC under extreme conditions and outperforms other inverse problem approaches used in DeepJSCC.

eess.IV↗

arXiv2023

Learning-Based Reconstruction of FRI Signals

Finite Rate of Innovation (FRI) sampling theory enables reconstruction of classes of continuous non-bandlimited signals that have a small number of free parameters from their low-rate discrete samples. This task is often translated into a spectral estimation problem that is solved using methods involving estimating signal subspaces, which tend to break down at a certain peak signal-to-noise ratio (PSNR). To avoid this breakdown, we consider alternative approaches that make use of information from labelled data. We propose two model-based learning methods, including deep unfolding the denoising process in spectral estimation, and constructing an encoder-decoder deep neural network that models the acquisition process. Simulation results of both learning algorithms indicate significant improvements of the breakdown PSNR over classical subspace-based methods. 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. We also achieve competitive results in detecting pulses from in vivo calcium imaging data in terms of true positive and false positive rate while providing more precise estimations.

eess.SP↗

arXiv2023

INDigo: An INN-Guided Probabilistic Diffusion Algorithm for Inverse Problems

Recently it has been shown that using diffusion models for inverse problems can lead to remarkable results. However, these approaches require a closed-form expression of the degradation model and can not support complex degradations. To overcome this limitation, we propose a method (INDigo) that combines invertible neural networks (INN) and diffusion models for general inverse problems. Specifically, we train the forward process of INN to simulate an arbitrary degradation process and use the inverse as a reconstruction process. During the diffusion sampling process, we impose an additional data-consistency step that minimizes the distance between the intermediate result and the INN-optimized result at every iteration, where the INN-optimized image is composed of the coarse information given by the observed degraded image and the details generated by the diffusion process. 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. Experiments demonstrate that our algorithm obtains competitive results compared with recently leading methods both quantitatively and visually. Moreover, our algorithm performs well on more complex degradation models and real-world low-quality images.

cs.CV↗

arXiv2022

Generative Joint Source-Channel Coding for Semantic Image Transmission

Recent works have shown that joint source-channel coding (JSCC) schemes using deep neural networks (DNNs), called DeepJSCC, provide promising results in wireless image transmission. However, these methods mostly focus on the distortion of the reconstructed signals with respect to the input image, rather than their perception by humans. However, focusing on traditional distortion metrics alone does not necessarily result in high perceptual quality, especially in extreme physical conditions, such as very low bandwidth compression ratio (BCR) and low signal-to-noise ratio (SNR) regimes. In this work, we propose two novel JSCC schemes that leverage the perceptual quality of deep generative models (DGMs) for wireless image transmission, namely InverseJSCC and GenerativeJSCC. While the former is an inverse problem approach to DeepJSCC, the latter is an end-to-end optimized JSCC scheme. In both, we optimize a weighted sum of mean squared error (MSE) and learned perceptual image patch similarity (LPIPS) losses, which capture more semantic similarities than other distortion metrics. InverseJSCC performs denoising on the distorted reconstructions of a DeepJSCC model by solving an inverse optimization problem using style-based generative adversarial network (StyleGAN). Our simulation results show that InverseJSCC significantly improves the state-of-the-art (SotA) DeepJSCC in terms of perceptual quality in edge cases. 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.

eess.IV↗