Open Thesis Proposals

  • Synthetic Lightfield Compression (master)

    Description: The world of lightfield represents a fascinating frontier in the field of photography and three-dimensional visualization. Lightfield cameras capture a scene from multiple viewpoints through an array of microlenses, allowing focus and perspective to be changed even after the image has been captured. This technology has applications in cinema, computer graphics, virtual and augmented reality, design, and medical simulation. Standardization organizations like JPEG and MPEG are developing technologies based on artificial intelligence (in particular deep neural networks) for the acquisition, compression, processing, and display of lightfields. Despite the potential of deep neural networks to process lightfield images, the limited availability of datasets poses a challenge. The creation of synthetic lightfield datasets through 3D modeling software like Blender3D is a promising solution. This project aims to study the functioning of lightfield cameras, generate synthetic datasets, and evaluate the quality of synthetic lightfield images by training neural networks for data compression and reconstruction.

    Contacts: Attilio Fiandrotti (attilio.fiandrotti@unito.it) Gianluca Dalmasso (gianluca.dalmasso@unito.it)


  • Internship in Internal Startup of Thales Alenia Space in Torino (master)

    Description: Thales Alenia Space in Torino is a key player of space exploration, currently involved in the development of many programs for Earth Orbit (EUCLID, Axiom Hotel) the Moon (Lunar Gateway, Argonaut Lunar Lander, Moon Village), Mars (ExoMars Rosalind Franklin) and beyond. As part of its Open Innovation, Thales Alenia Space increased its Space Business Catalyst footprint by implementing an antenna in Torino to cover activities of the domain Exploration and Science. Incubated in the Space Business Catalyst in Torino, the first Italian, internal startup, Sparks, to find new business in non-core areas. The team is therefore recruiting an intern to support them in these activities. Join us on its innovative mission to democratize space exploration! We are developing a unique Space-themed digital crowdfunding platform, mixing space education and mobile casual video games in an edutaining and playful manner. Our project lies at the crossroads of blockchain technology and edutainment, aiming to build a unified, cooperative, and expansive Space community globally. If you share our passion for technology, education, and space exploration, this is the perfect opportunity for you!

    Contacts: Luca Simonini (luca.simonini@thalesaleniaspace.com) Agata Soccini (agatamarta.soccini@unito.it)


  • Robust AI-based Video Compression (master/bachelor)

    Description: Nowadays over 60% of the whole Internet traffic is represented by video communications, therefore efficient video compression techniques able to relieve the pressure on the network infrastructure are in demand. Over the past years, the deep learning paradigm has enjoyed tremendous success in a number of fields, including image and video compression [2]. AI-based video codecs built atop of deep neural architectures nowadays achieve compression efficiency not far from standardized video codecs [3] such as MPEG H.264/AVC (DVBT) or H.265/HEVC (DVBT2). However, existing research in the field focuses mainly on improving the compression efficiency, whereas the issues related to the transmission of the AI-compressed video over unreliable channels (e.g., wireless channels affected by noise or packet networks affected by router congestion) have been explored little. This thesis proposal lies at the boundary between AI, deep learning and image compression and aims at investigating the effect of data losses over the transmitted video as a first step, and devising robust learnable encoding algorithms as a potential further step. The ideal profile includes knowledge of deep learning techniques on one side and familiarity with video coding methods on the other and familiarity with the Python language.

    Contacts: Attilio Fiandrotti (attilio.fiandrotti@unito.it) Valerio Bioglio (valerio.bioglio@unito.it)


  • Edge AI for Inertial Measurement Unit (IMU) event classification (master/bachelor) [pdf]

    Description: The student will be involved in the development of embedded AI algorithm to detect acceleration pattern for human activity and object motions. The thesis project aims to develop ML/DL algorithms able to classify different IMU signals pattern enabling safety procedure in micro- mobility use cases.

    Contacts: Marcello Babbi (m.babbi@reply.it) Attilio Fiandrotti (attilio.fiandrotti@unito.it)


  • Enhancing Privacy and Security in Face Recognition Through Synthetic Dataset Generation (master/bachelor) [pdf]

    Description: The proliferation of face recognition technologies has raised significant concerns about privacy and security. While face recognition systems offer numerous benefits in various domains, they often rely on vast and sensitive datasets, giving rise to ethical and privacy challenges. This thesis proposal aims to address these issues developing a secure and privacy-compliant solution through the creation of synthetic datasets for face recognition, leveraging generative AI techniques.

    Contacts: Marcello Babbi (m.babbi@reply.it) Attilio Fiandrotti (attilio.fiandrotti@unito.it)


  • Transformer optimization for edge deployment (master/bachelor) [pdf]

    Description: Transformer models have become a dominant architecture in machine learning, achieving state-of-the-art results in many domains, including Computer Vision. However, their large model sizes make them difficult to deploy on low- powered devices. This thesis proposes a method for implementing a Visual Transformer on embedded platforms (e.g. MCU), optimizing model complexity with performance and inference time.

    Contacts: Marcello Babbi (m.babbi@reply.it) Attilio Fiandrotti (attilio.fiandrotti@unito.it)


  • Multi-target stain normalization for histopathology (master/bachelor) [pdf]

    Description: Develop and implement novel techniques for stain normalization in histological images for deep learning applications.

    Contacts: carlo.barbano@unito.it marco.grangetto@unito.it


Past Thesis

2023

  • Reinforcement Learning per l’addestramento di un Self-Driving Agent: Algoritmi e Sperimentazioni, Daniele Migliore Camilleri, 2023. Supervisor: Marco Grangetto. Co-supervisor: Mirko Zaffaroni

  • Deep Learning on Histopathological Images for Colorectal Cancer grading, Alessandro Caputo, 2023. Supervisor: Francesca Cordero. Co-supervisors: Carlo Alberto Barbano, Marco Grangetto.

  • Towards Non-invasive Stroke Diagnosis: A Neural Network Approach to CT Perfusion Imaging With Subsampling, Miriam Fasciana, 2023. Supervisor: Marco Grangetto. Co-supervisor: Riccardo Renzulli.

  • Capsule Networks for Lung Nodules Segmentation, Paolo Peretti, 2023. Supervisor: Marco Grangetto. Co-supervisor: Riccardo Renzulli.

2022

  • Detection of Ovarian Cancer from Ultrasound Scans using Deep Learning: from Raw to Ready-to-Use Medical Dataset, Pio Raffaele Fina, 2022. Supervisor: Marco Grangetto. Co-supervisor: Carlo Alberto Barbano. Examiner: Federica Gerace. [abs]

  • Deep Learning-based prediction of coronary calcium from X-rays, Francesco Iodice, 2022. Supervisor: Marco Grangetto. Co-Supervisors: Alberto Presta, Carlo Alberto Barbano. [abs]

  • Automated PCB Components Fault Detection Using Deep-Learning, Gabriele Spadaro, 2022. Supervisor: Attilio Fiandrotti. [abs]

  • Efficient Transformer Architectures for Sentiment Analysis in Italian, Luca Molinaro, 2022. Supervisor: Attilio Fiandrotti. [abs]

  • Synthetic Training of Artificial Neural Networks for Object Detection in Retail, Gianluca Dalmasso, 2022. Supervisor: Attilio Fiandrotti. Co-Supervisor: Andrea Bragagnolo [abs]

  • Generative Adversarial Networks for Histopathological Image Synthesis and Augmentation, Desislav Nikolaev Ivanov, 2022. Supervisor: Marco Grangetto. Co-Supervisor: Carlo Alberto Barbano. Examiner: Francesca Cordero. [abs]

  • Recognition and analysis of price tags in retailenvironment through neural networks trainedwith synthetic datasets, Luca Gerbaudo, 2022. Supervisors: Marco Grangetto. Co-Supervisor: Andrea Bragagnolo. [abs]

  • Deep Learning Methods for Anomaly Detection on Time Series ​, Alessandro Nassi, 2022. Supervisors: Marco Grangetto, Idilio Drago. [abs]

  • Covid-19 detection from Chest X-ray images using Deep Learning, Giuseppe Stallone, 2022. Supervisors: Marco Grangetto. Co-Supervisors: Carlo Alberto Barbano, Enzo Tartaglione. [abs]

2021

  • Encoding rotation representations of synthetic datasets in quaternions-based deep learning models., Alessandro Grassi, 2021. Supervisors: Marco Grangetto. Co-Supervisor: Riccardo Renzulli. [abs]

  • Preprocessing tools for Chest X-Ray images., Andrè Tuninetti, 2021. Supervisors: Marco Grangetto. Co-Supervisor: Enzo Tartaglione. [abs]

  • Lung nodules segmentation from CT scans using deep learning., Stefano Berti, 2021. Supervisors: Marco Grangetto. Co-Supervisor: Riccardo Renzulli. Examiner: Enzo Tartaglione. [abs]

  • Semantic segmentation of histopathological tissue with Deep Learning, Davide Di Luccio, 2021. Supervisors: Marco Grangetto, Attilio Fiandrotti. Co-Supervisors: Carlo Alberto Barbano, Enzo Tartaglione. [abs]

  • Analysis and development of synthetic datasets for ML-based retail applications, Luca Pregno, 2021. Supervisor: Ferruccio Damiani. Co-supervisors: Andrea Basso, Andrea Bragagnolo. Examiner: Marco Grangetto. [abs]

  • Generation of histopathological tissue with Generative Adversarial Network, Davide Rubinetti, 2021. Supervisors: Roberto Esposito, Marco Grangetto. Co-Supervisors: Carlo Alberto Barbano, Enzo Tartaglione. [abs]

  • Facial Verification In Digital Onboarding Process, Marco Carico, 2021. Supervisor: Attilio Fiandrotti. [abs]

  • Optimization of Neural Networks in Mobile Devices, Francesco Vottari, 2021. Supervisor: Ferruccio Damiani. Co-supervisors: Andrea Basso, Andrea Bragagnolo. Examiner: Attilio Fiandrotti. [abs]