Publications associées à New Techniques for the Digitization of Art Historical Photographic Archives - the Case of the Cini Foundation in Venice

Aggregating Spatial and Photometric Context for Photometric Stereo

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

EPFL2024

Assessment framework for deepfake detection in real-world situations

Touradj Ebrahimi, Yuhang Lu

Detecting digital face manipulation in images and video has attracted extensive attention due to the potential risk to public trust. To counteract the malicious usage of such techniques, deep learning-based deepfake detection methods have been employed and ...

2024

A KL Divergence-Based Loss for In Vivo Ultrafast Ultrasound Image Enhancement with Deep Learning

Jean-Philippe Thiran, Roser Vinals Terres

Ultrafast ultrasound imaging, characterized by high frame rates, generates low-quality images. Convolutional neural networks (CNNs) have demonstrated great potential to enhance image quality without compromising the frame rate. However, CNNs have been most ...

2023

Towards learning-based denoising of light fields

Touradj Ebrahimi, Michela Testolina, Tomás Soares De Carvalho Feith

In recent years, new emerging immersive imaging modalities, e.g. light fields, have been receiving growing attention, becoming increasingly widespread over the years. Light fields are often captured through multi-camera arrays or plenoptic cameras, with th ...

2023

3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping

Siyuan Li, Zhuoqian Yang

We present 3DHumanGAN, a 3D-aware generative adversarial network that synthesizes photo-like images of fullbody humans with consistent appearances under different view-angles and body-poses. To tackle the representational and computational challenges in sy ...

Ieee Computer Soc2023

Exploiting Explanations to Detect Misclassifications of Deep Learning Models in Power Grid Visual Inspection

Olga Fink, Giovanni Floreale

In the context of automatic visual inspection of infrastructures by drones, Deep Learning (DL) models are used to automatically process images for fault diagnostics. While explainable Artificial Intelligence (AI) algorithms can provide explanations to asse ...

Research Publishing2023

Self-Supervised Learning for Patient Stratification and Survival Analysis in Computational Pathology: An Application to Colorectal Cancer

Christian Robert Abbet

Over the years, clinical institutes accumulated large amounts of digital slides from resected tissue specimens. These digital images, called whole slide images (WSIs), are high-resolution tissue snapshots that depict the complex interaction of cells at the ...

EPFL2023

3D reconstruction of curvilinear one-dimensional objects viewed in transmission electron microscopy

Gulnaz Ganeeva

To obtain a more complete understanding of material microstructure at the nanoscale and to gain profound insights into their properties, there is a growing need for more efficient and precise methods that can streamline the process of 3D imaging using a tr ...

EPFL2023

On Artificial Intelligence and Manipulation

Marcello Ienca

The increasing diffusion of novel digital and online sociotechnical systems for arational behavioral influence based on Artificial Intelligence (AI), such as social media, microtargeting advertising, and personalized search algorithms, has brought about ne ...

SPRINGER2023

X-ray imaging detector for radiological applications adapted to the context and requirements of low- and middle-income countries

Klaus Benedikt Schönenberger, Hubert Blanchard, René Salathé, Jean-Philippe Thiran, Romain Sahli, Sébastien Emmanuel Blanc, Mario Andres Chavarria Varon, Matthias Hüser, Jérôme Schmid

This paper describes the development of a novel medical x-ray imaging system adapted to the needs and constraints of low- and middle-income countries. The developed system is based on an indirect conversion chain: a scintillator plate produces visible ligh ...

2022

On combining denoising with learning-based image decoding

Touradj Ebrahimi, Michela Testolina

Noise is an intrinsic part of any sensor and is present, in various degrees, in any content that has been captured in real life environments. In imaging applications, several pre- and post-processing solutions have been proposed to cope with noise in captu ...

SPIE2022

Attribute Prediction as Multiple Instance Learning

Devis Tuia, Diego Marcos Gonzalez

Attribute-based representations help machine learning models perform tasks based on human understandable concepts, allowing a closer human-machine collaboration. However, learning attributes that accurately reflect the content of an image is not always str ...

2022

Generating macrocyclic inhibitors of protein-protein interactions

Gontran Sangouard

Protein-protein interactions (PPIs) play important roles in many diseases and their modulation is an attractive strategy for developing new therapeutics. However, the relatively large and often flat binding surfaces of PPIs makes the development of inhibit ...

EPFL2022

OSLO: On-the-Sphere Learning for Omnidirectional Images and Its Application to 360-Degree Image Compression

Pascal Frossard, Thomas Maugey, Roberto Gerson De Albuquerque Azevedo

State-of-the-art 2D image compression schemes rely on the power of convolutional neural networks (CNNs). Although CNNs offer promising perspectives for 2D image compression, extending such models to omnidirectional images is not straightforward. First, omn ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

Differentiable inverse rendering based on radiative backpropagation

Merlin Eléazar Nimier-David, Wenzel Alban Jakob

A computer-implemented inverse rendering method is provided. The method comprises: computing an adjoint image by differentiating an objective function that evaluates the quality of a rendered image, image elements of the adjoint image encoding the sensitiv ...

2021

Counting People by Estimating People Flows

Pascal Fua, Mathieu Salzmann, Weizhe Liu

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness co ...

2022

A Pixel Design of a Branching Ultra-Highspeed Image Sensor

Edoardo Charbon

A burst image sensor named Hanabi, meaning fireworks in Japanese, includes a branching CCD and multiple CMOS readout circuits. The sensor is backside-illuminated with a light/charge guide pipe to minimize the temporal resolution by suppressing the horizont ...

2021

Une approche computationnelle du cadastre napoléonien de Venise

Frédéric Kaplan, Raphaël Barman, Isabella Di Lenardo, Federica Pardini

At the beginning of the 19th century, the Napoleonic administration introduced a new standardised description system to give an objective account of the form and functions of the city of Venice. The cadastre, deployed on a European scale, was offering for ...

2021

3DPD: A photogrammetric pipeline for a PUSH frame stereo cameras

Nicolas Le Thomas

An innovative photogrammetric pipeline has been developed by INAF-Padova for the processing of the stereo images from the CaSSIS (Colour and Stereo Imaging System) (Thomas et al., 2014). CaSSIS is the multispectral stereo push frame camera on board ExoMars ...

PERGAMON-ELSEVIER SCIENCE LTD2021

Tracking and Relative Localization of Drone Swarms With a Vision-Based Headset

Dario Floreano, Giuseppe Loianno, Maxim Pavliv, Fabrizio Schiano

We address the detection, tracking, and relative localization of the agents of a drone swarm from a human perspective using a headset equipped with a single camera and an Inertial Measurement Unit (IMU). We train and deploy a deep neural network detector o ...

2021