arXiv subjects

Claudio Ferrari

Publications and source records attributed to Claudio Ferrari.

35 records · Page 2Linked to original sources

arXiv2024

Recent developments in Laue lens manufacturing and their impact on imaging performance

We report on recent progress in the development of Laue lenses for applications in hard X/soft gamma-ray astronomy. Here we focus on the realization of a sector of such a lens made of 11 bent Germanium crystals and describe the technological challenges involved in their positioning and alignment with adhesive-based bonding techniques. The accurate alignment and the uniformity of the curvature of the crystals are critical for achieving optimal X-ray focusing capabilities. We have assessed how the errors of misalignment with respect to the main orientation angles of the crystals affect the point spread function (PSF) of the image diffracted by a single sector. We have corroborated these results with simulations carried out with our physical model of the lens, based on a Monte Carlo ray-tracing technique, adopting the geometrical configuration of the Laue sector, the observed assembly accuracy and the measured curvatures of the crystals. An extrapolation of the performances achieved on a single sector to an entire Laue lens based on this model has shown that a PSF with half-power-diameter of 4.8 arcmin can be achieved with current technology. This has the potential to lead to a significant improvement in sensitivity of spectroscopic and polarimetric observations in the 50-600 keV band

astro-ph.IM↗

arXiv2023

The TRILL project: increasing the technological readiness of Laue lenses

Hard X-/soft Gamma-ray astronomy (> 100 keV) is a crucial field for the study of important astrophysical phenomena such as the 511 keV positron annihilation line in the Galactic center region and its origin, gamma-ray bursts, soft gamma-ray repeaters, nuclear lines from SN explosions and more. However, several key questions in this field require sensitivity and angular resolution that are hardly achievable with present technology. A new generation of instruments suitable to focus hard X-/soft Gamma-rays is necessary to overcome the technological limitations of current direct-viewing telescopes. One solution is using Laue lenses based on Bragg's diffraction in a transmission configuration. To date, this technology is in an advanced stage of development and further efforts are being made in order to significantly increase its technology readiness level (TRL). To this end, massive production of suitable crystals is required, as well as an improvement of the capability of their alignment. Such a technological improvement could be exploited in stratospheric balloon experiments and, ultimately, in space missions with a telescope of about 20 m focal length, capable of focusing over a broad energy pass-band. We present the latest technological developments of the TRILL (Technological Readiness Increase for Laue Lenses) project, supported by ASI, devoted to the advancement of the technological readiness of Laue lenses. We show the method we developed for preparing suitable bent Germanium and Silicon crystals and the latest advancements in crystals alignment technology.

astro-ph.IM↗

arXiv2023

Learning Landmarks Motion from Speech for Speaker-Agnostic 3D Talking Heads Generation

This paper presents a novel approach for generating 3D talking heads from raw audio inputs. Our method grounds on the idea that speech related movements can be comprehensively and efficiently described by the motion of a few control points located on the movable parts of the face, i.e., landmarks. The underlying musculoskeletal structure then allows us to learn how their motion influences the geometrical deformations of the whole face. The proposed method employs two distinct models to this aim: the first one learns to generate the motion of a sparse set of landmarks from the given audio. The second model expands such landmarks motion to a dense motion field, which is utilized to animate a given 3D mesh in neutral state. Additionally, we introduce a novel loss function, named Cosine Loss, which minimizes the angle between the generated motion vectors and the ground truth ones. Using landmarks in 3D talking head generation offers various advantages such as consistency, reliability, and obviating the need for manual-annotation. Our approach is designed to be identity-agnostic, enabling high-quality facial animations for any users without additional data or training.

cs.CV↗

arXiv2023

Automatic Generation of Semantic Parts for Face Image Synthesis

Semantic image synthesis (SIS) refers to the problem of generating realistic imagery given a semantic segmentation mask that defines the spatial layout of object classes. Most of the approaches in the literature, other than the quality of the generated images, put effort in finding solutions to increase the generation diversity in terms of style i.e. texture. However, they all neglect a different feature, which is the possibility of manipulating the layout provided by the mask. Currently, the only way to do so is manually by means of graphical users interfaces. In this paper, we describe a network architecture to address the problem of automatically manipulating or generating the shape of object classes in semantic segmentation masks, with specific focus on human faces. Our proposed model allows embedding the mask class-wise into a latent space where each class embedding can be independently edited. Then, a bi-directional LSTM block and a convolutional decoder output a new, locally manipulated mask. We report quantitative and qualitative results on the CelebMask-HQ dataset, which show our model can both faithfully reconstruct and modify a segmentation mask at the class level. Also, we show our model can be put before a SIS generator, opening the way to a fully automatic generation control of both shape and texture. Code available at https://github.com/TFonta/Semantic-VAE.

cs.CV↗

arXiv2023

Generating Multiple 4D Expression Transitions by Learning Face Landmark Trajectories

In this work, we address the problem of 4D facial expressions generation. This is usually addressed by animating a neutral 3D face to reach an expression peak, and then get back to the neutral state. In the real world though, people show more complex expressions, and switch from one expression to another. We thus propose a new model that generates transitions between different expressions, and synthesizes long and composed 4D expressions. This involves three sub-problems: (i) modeling the temporal dynamics of expressions, (ii) learning transitions between them, and (iii) deforming a generic mesh. We propose to encode the temporal evolution of expressions using the motion of a set of 3D landmarks, that we learn to generate by training a manifold-valued GAN (Motion3DGAN). To allow the generation of composed expressions, this model accepts two labels encoding the starting and the ending expressions. The final sequence of meshes is generated by a Sparse2Dense mesh Decoder (S2D-Dec) that maps the landmark displacements to a dense, per-vertex displacement of a known mesh topology. By explicitly working with motion trajectories, the model is totally independent from the identity. Extensive experiments on five public datasets show that our proposed approach brings significant improvements with respect to previous solutions, while retaining good generalization to unseen data.

cs.CV↗

arXiv2023

Opening the path to hard X-/soft gamma-ray focussing: the ASTENA-pathfinder mission

Hard X-/soft gamma-ray astronomy is a crucial field for transient, nuclear and multimessenger astrophysics. However, the spatial localization, imaging capabilities and sensitivity of the measurements are strongly limited for the energy range > 70 keV. To overcome these limitations, we have proposed a mission concept, ASTENA, submitted to ESA for its program Voyage 2050. We will report on a pathfinder of ASTENA, that we intend to propose to ASI as an Italian mission with international participation. It will be based on one of the two instruments aboard ASTENA: a Laue lens with 20 m focal length, able to focus hard X-rays in the 50-700 keV passband into a 3-d position sensitive focal plane spectrometer. The combination of the focussing properties of the lens and of the localization properties of the detector will provide unparalleled imaging and spectroscopic capabilities, thus enabling studies of phenomena such as gamma-ray bursts afterglows, supernova explosions, positron annihilation lines and many more.

astro-ph.IM↗

arXiv2022

What makes you, you? Analyzing Recognition by Swapping Face Parts

Deep learning advanced face recognition to an unprecedented accuracy. However, understanding how local parts of the face affect the overall recognition performance is still mostly unclear. Among others, face swap has been experimented to this end, but just for the entire face. In this paper, we propose to swap facial parts as a way to disentangle the recognition relevance of different face parts, like eyes, nose and mouth. In our method, swapping parts from a source face to a target one is performed by fitting a 3D prior, which establishes dense pixels correspondence between parts, while also handling pose differences. Seamless cloning is then used to obtain smooth transitions between the mapped source regions and the shape and skin tone of the target face. We devised an experimental protocol that allowed us to draw some preliminary conclusions when the swapped images are classified by deep networks, indicating a prominence of the eyes and eyebrows region. Code available at https://github.com/clferrari/FacePartsSwap

cs.CV↗

arXiv2022

Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound

State-of-the-art neural network verifiers are fundamentally based on one of two paradigms: either encoding the whole verification problem via tight multi-neuron convex relaxations or applying a Branch-and-Bound (BaB) procedure leveraging imprecise but fast bounding methods on a large number of easier subproblems. The former can capture complex multi-neuron dependencies but sacrifices completeness due to the inherent limitations of convex relaxations. The latter enables complete verification but becomes increasingly ineffective on larger and more challenging networks. In this work, we present a novel complete verifier which combines the strengths of both paradigms: it leverages multi-neuron relaxations to drastically reduce the number of subproblems generated during the BaB process and an efficient GPU-based dual optimizer to solve the remaining ones. An extensive evaluation demonstrates that our verifier achieves a new state-of-the-art on both established benchmarks as well as networks with significantly higher accuracy than previously considered. The latter result (up to 28% certification gains) indicates meaningful progress towards creating verifiers that can handle practically relevant networks.

cs.LG↗

arXiv2022

Sparse to Dense Dynamic 3D Facial Expression Generation

In this paper, we propose a solution to the task of generating dynamic 3D facial expressions from a neutral 3D face and an expression label. This involves solving two sub-problems: (i)modeling the temporal dynamics of expressions, and (ii) deforming the neutral mesh to obtain the expressive counterpart. We represent the temporal evolution of expressions using the motion of a sparse set of 3D landmarks that we learn to generate by training a manifold-valued GAN (Motion3DGAN). To better encode the expression-induced deformation and disentangle it from the identity information, the generated motion is represented as per-frame displacement from a neutral configuration. To generate the expressive meshes, we train a Sparse2Dense mesh Decoder (S2D-Dec) that maps the landmark displacements to a dense, per-vertex displacement. This allows us to learn how the motion of a sparse set of landmarks influences the deformation of the overall face surface, independently from the identity. Experimental results on the CoMA and D3DFACS datasets show that our solution brings significant improvements with respect to previous solutions in terms of both dynamic expression generation and mesh reconstruction, while retaining good generalization to unseen data. The code and the pretrained model will be made publicly available.

cs.CV↗

arXiv2022

Instance-wise algorithm configuration with graph neural networks

We present our submission for the configuration task of the Machine Learning for Combinatorial Optimization (ML4CO) NeurIPS 2021 competition. The configuration task is to predict a good configuration of the open-source solver SCIP to solve a mixed integer linear program (MILP) efficiently. We pose this task as a supervised learning problem: First, we compile a large dataset of the solver performance for various configurations and all provided MILP instances. Second, we use this data to train a graph neural network that learns to predict a good configuration for a specific instance. The submission was tested on the three problem benchmarks of the competition and improved solver performance over the default by 12% and 35% and 8% across the hidden test instances. We ranked 3rd out of 15 on the global leaderboard and won the student leaderboard. We make our code publicly available at \url{https://github.com/RomeoV/ml4co-competition} .

cs.LG↗

arXiv2021

A Sparse and Locally Coherent Morphable Face Model for Dense Semantic Correspondence Across Heterogeneous 3D Faces

The 3D Morphable Model (3DMM) is a powerful statistical tool for representing 3D face shapes. To build a 3DMM, a training set of face scans in full point-to-point correspondence is required, and its modeling capabilities directly depend on the variability contained in the training data. Thus, to increase the descriptive power of the 3DMM, establishing a dense correspondence across heterogeneous scans with sufficient diversity in terms of identities, ethnicities, or expressions becomes essential. In this manuscript, we present a fully automatic approach that leverages a 3DMM to transfer its dense semantic annotation across raw 3D faces, establishing a dense correspondence between them. We propose a novel formulation to learn a set of sparse deformation components with local support on the face that, together with an original non-rigid deformation algorithm, allow the 3DMM to precisely fit unseen faces and transfer its semantic annotation. We extensively experimented our approach, showing it can effectively generalize to highly diverse samples and accurately establish a dense correspondence even in presence of complex facial expressions. The accuracy of the dense registration is demonstrated by building a heterogeneous, large-scale 3DMM from more than 9,000 fully registered scans obtained by joining three large datasets together.

cs.CV↗

arXiv2020

Semantic Segmentation of Histopathological Slides for the Classification of Cutaneous Lymphoma and Eczema

Mycosis fungoides (MF) is a rare, potentially life threatening skin disease, which in early stages clinically and histologically strongly resembles Eczema, a very common and benign skin condition. In order to increase the survival rate, one needs to provide the appropriate treatment early on. To this end, one crucial step for specialists is the evaluation of histopathological slides (glass slides), or Whole Slide Images (WSI), of the patients' skin tissue. We introduce a deep learning aided diagnostics tool that brings a two-fold value to the decision process of pathologists. First, our algorithm accurately segments WSI into regions that are relevant for an accurate diagnosis, achieving a Mean-IoU of 69% and a Matthews Correlation score of 83% on a novel dataset. Additionally, we also show that our model is competitive with the state of the art on a reference dataset. Second, using the segmentation map and the original image, we are able to predict if a patient has MF or Eczema. We created two models that can be applied in different stages of the diagnostic pipeline, potentially eliminating life-threatening mistakes. The classification outcome is considerably more interpretable than using only the WSI as the input, since it is also based on the segmentation map. Our segmentation model, which we call EU-Net, extends a classical U-Net with an EfficientNet-B7 encoder which was pre-trained on the Imagenet dataset.

eess.IV↗

arXiv2020

Inner Eye Canthus Localization for Human Body Temperature Screening

In this paper, we propose an automatic approach for localizing the inner eye canthus in thermal face images. We first coarsely detect 5 facial keypoints corresponding to the center of the eyes, the nosetip and the ears. Then we compute a sparse 2D-3D points correspondence using a 3D Morphable Face Model (3DMM). This correspondence is used to project the entire 3D face onto the image, and subsequently locate the inner eye canthus. Detecting this location allows to obtain the most precise body temperature measurement for a person using a thermal camera. We evaluated the approach on a thermal face dataset provided with manually annotated landmarks. However, such manual annotations are normally conceived to identify facial parts such as eyes, nose and mouth, and are not specifically tailored for localizing the eye canthus region. As additional contribution, we enrich the original dataset by using the annotated landmarks to deform and project the 3DMM onto the images. Then, by manually selecting a small region corresponding to the eye canthus, we enrich the dataset with additional annotations. By using the manual landmarks, we ensure the correctness of the 3DMM projection, which can be used as ground-truth for future evaluations. Moreover, we supply the dataset with the 3D head poses and per-point visibility masks for detecting self-occlusions. The data will be publicly released.

cs.CV↗

arXiv2019

Additional Baseline Metrics for the paper "Extended YouTube Faces: a Dataset for Heterogeneous Open-Set Face Identification"

In this report, we provide additional and corrected results for the paper "Extended YouTube Faces: a Dataset for Heterogeneous Open-Set Face Identification". After further investigations, we discovered and corrected wrongly labeled images and incorrect identities. This forced us to re-generate the evaluation protocol for the new data; in doing so, we also reproduced and extended the experimental results with other standard metrics and measures used in the literature. The reader can refer to the original paper for additional details regarding the data collection procedure and recognition pipeline.

cs.CV↗

arXiv2019

Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making

We draw attention to an important, yet largely overlooked aspect of evaluating fairness for automated decision making systems---namely risk and welfare considerations. Our proposed family of measures corresponds to the long-established formulations of cardinal social welfare in economics, and is justified by the Rawlsian conception of fairness behind a veil of ignorance. The convex formulation of our welfare-based measures of fairness allows us to integrate them as a constraint into any convex loss minimization pipeline. Our empirical analysis reveals interesting trade-offs between our proposal and (a) prediction accuracy, (b) group discrimination, and (c) Dwork et al.'s notion of individual fairness. Furthermore and perhaps most importantly, our work provides both heuristic justification and empirical evidence suggesting that a lower-bound on our measures often leads to bounded inequality in algorithmic outcomes; hence presenting the first computationally feasible mechanism for bounding individual-level inequality.

cs.AI↗

arXiv2016

BEaTriX, expanded X-ray beam facility for testing modular elements of telescope optics: an update

We present in this paper an update on the design of BEaTriX (Beam Expander Testing X-ray facility), an X-ray apparatus to be realized at INAF/OAB and that will generate an expanded, uniform and parallel beam of soft X-rays. BEaTriX will be used to perform the functional tests of X-ray focusing modules of large X-ray optics such as those for the ATHENA X-ray observatory, using the Silicon Pore Optics (SPO) as a baseline technology, and Slumped Glass Optics (SGO) as a possible alternative. Performing the tests in X-rays provides the advantage of an in-situ, at-wavelength quality control of the optical modules produced in series by the industry, performing a selection of the modules with the best angular resolution, and, in the case of SPOs, there is also the interesting possibility to align the parabolic and the hyperbolic stacks directly under X-rays, to minimize the aberrations. However, a parallel beam with divergence below 2 arcsec is necessary in order to measure mirror elements that are expected to reach an angular resolution of about 4 arcsec, since the ATHENA requirement for the entire telescope is 5 arcsec. Such a low divergence over the typical aperture of modular optics would require an X-ray source to be located in a several kilometers long vacuum tube. In contrast, BEaTriX will be compact enough (5 m x 14 m) to be housed in a small laboratory, will produce an expanded X-ray beam 60 mm x 200 mm broad, characterized by a very low divergence (1.5 arcsec HEW), strong polarization, high uniformity, and X-ray energy selectable between 1.5 keV and 4.5 keV. In this work we describe the BEaTriX layout and show a performance simulation for the X-ray energy of 4.5 keV.

astro-ph.IM↗

arXiv2012

Analytical modeling for the heat transfer in sheared flows of nanofluids

We developed a model for the enhancement of the heat flux by spherical and elongated nano- particles in sheared laminar flows of nano-fluids. Besides the heat flux carried by the nanoparticles the model accounts for the contribution of their rotation to the heat flux inside and outside the particles. The rotation of the nanoparticles has a twofold effect, it induces a fluid advection around the particle and it strongly influences the statistical distribution of particle orientations. These dynamical effects, which were not included in existing thermal models, are responsible for changing the thermal properties of flowing fluids as compared to quiescent fluids. The proposed model is strongly supported by extensive numerical simulations, demonstrating a potential increase of the heat flux far beyond the Maxwell-Garnet limit for the spherical nanoparticles. The road ahead which should lead towards robust predictive models of heat flux enhancement is discussed.

physics.flu-dyn↗