Thesis Proposals

Virtual, Augmented and Mixed Reality

    • Thesis with an external company

      Virtual/Augmented reality for emergency management

      Supervisors: Fabrizio Lamberti
      Several thesis proposals are available. The objective will be the implementation of scenarios (environments) to be used in the context of immersive Virtual Reality settings and Augmented Reality applications for education and training through modeling, animation and coding techniques. The activities could focus on one of the following domains: air force (with a focus on training of operators, in collaboration ...
    • Thesis at Politecnico di Torino

      Virtual laboratories based on immersive VR and Web technologies

      Supervisors: Fabrizio Lamberti
      A "virtual laboratory" is defined as an interactive environment that enables a group of researchers located around the world to work together for creating and conducting simulated experiments. Virtual laboratories are receiving an increasing attention also by the world of education, as they could represent the practical side of online classes that are implemented today according to the Massive Open Online ...
    • Thesis at Politecnico di Torino

      Virtual equine respiratory endoscopy system for educational purposes in veterinary medicine

      Supervisors: Fabrizio Lamberti
      Respiratory endoscopy is a frequently performed exam in equine medicine. The learning curve for performing endoscopic procedures is made up by the sum of the acquisition of medical knowledge and technical/manual expertise. The latter is significantly hampered by the paucity of occasions during which the students can perform themselves the procedure in educational settings. In this context, the thesis aims to ...
    • Thesis at Politecnico di Torino

      User experience with connected and autonomous vehicles in simulated, virtual reality-based environments

      Several thesis proposals in the areas of Computer Graphics & Virtual Reality as well as of Machine Learning & Signal Interpretation are available. The goal of these proposals will be to investigate the broad design space of Human-Machine Interaction (HMI) techniques for Connected and Autonomous Vehicles (CAVs) tailored to the establishment of trust between the users and the vehicle through the creation of an ...
    • Thesis with an external company

      Mixed reality technology for industrial training

      Supervisors: Fabrizio Lamberti
      More than one proposal is available on this topic. The objective will be the implementation of scenarios (environments) to be used in the context of immersive Virtual Reality settings and Augmented Reality applications through modeling, animation and coding techniques. The activities could focus on either energy assessment for Industry 4.0 (in the frame of a European project in the automotive context in ...
    • Thesis at Politecnico di Torino

      An authoring tool for Virtual Reality applications supporting multiple usage configurations

      Supervisors: Fabrizio Lamberti
      Often, approaches or tools are used in the development of interactive graphics applications that let them be deployed on multiple platforms (desktop, browser, mobile, etc.). This is true also for Virtual Reality (VR) applications, that can (almost) seamlessly be used with different VR suites (HTC Vive, Oculus, etc.). However, VR hardware can offer very different functionalities to users, especially in terms ...
    • Thesis at Politecnico di Torino

      Believable avatars for virtual reality experiences in the medical domain

      Supervisors: Fabrizio Lamberti
      This proposal frames into a long-standing collaboration between the GRAINS group and the University of Ontario, Institute of Technology (UOIT), Canada and refers to activities that could be carried out either at Politecnico di Torino or at UOIT (in the latter case, the page on the Portale della Didattica regarding proposals for thesis abroad shall be checked). More than one positions are therefore available. ...
    • Thesis at Politecnico di Torino

      Natural proxy techniques for manipulative micro-interactions in Virtual Environments

      Supervisors: Fabrizio Lamberti,
      Interacting with objects is a fundamental task in immersive Virtual Reality (VR). For that reason, many paradigms and design guidelines for interactable objects are already used in VR applications to surmount the limitations of current VR technology (hand-tracking, wearable controllers, gaze) in terms of interaction capabilities. Nevertheless, there are applications in which adapting the design of the virtual ...
    • Thesis at Politecnico di Torino

      Note-taking tools for Virtual and Mixed Reality Training systems

      Supervisors: Fabrizio Lamberti,
      It is a quite common habit for many students and trainees to take notes during lectures. Nowadays, independently of the kind of notes made (annotation on didactic material, original text, schemes, etc.), the two prevalent approaches to produce notes are handwriting (on paper or digital supports) and keyboard typing (on writing software). However, due to the technological limitations and specificities of ...
    • Thesis at Politecnico di Torino

      Dealing with frequent looking out of the FOV limits of Head-Mounted Displays

      Supervisors: Fabrizio Lamberti,
      Immersive Virtual Reality (VR) headsets (HMD) are commonly capable of FOV of about 100°. Few ones are able to better fit the human range of 220°, but at a remarkable higher cost, weight and bulkiness. For many application scenarios indeed the limited FOV is more than adequate to fulfill the required task. In some other application instead, such as cockpit simulators, the trainee has the need to frequently ...
    • Thesis with an external company

      VR prototyping of the cockpit for eVTOL vehicles

      Supervisors: Fabrizio Lamberti
      The thesis / internship will have the goal to achieve the basic competences concerning the new segment of eVTOL (electrical Vertical Take-Off and Landing) vehicles, studying the human-machine interfaces to be implemented for the cockpit. With the support of aeronautics engineers, the student will be involved in the definition of the high-level architecture for onboard systems that need to be controlled by the ...

Computer Graphics, Computer Animation and Human-Machine Interaction

    • Thesis at Politecnico di Torino

      Animating Virtual Characters into Immersive Environments

      Generating computer animations, particularly of virtual characters, is a very labor-intensive task, which requires animators to operate with sophisticated interfaces. Hence, researchers continuously experiment with alternative interaction paradigms that could possibly ease the above task. Among others, sketching represents a valid alternative to traditional interfaces since it can make interactions more ...
    • Thesis at Politecnico di Torino

      A virtual agent for learning how to use Blender

      Modeling and animation suites, like Blender or Autodesk Maya, are de facto the standard software used by professional developers to generate virtual/animated scenes. Although they provide high flexibility in terms of available functionalities, they are usually characterized by a step-learning curve. The difficulties in using these suites make them not accessible to novice users. The goal behind this thesis is ...
    • Thesis at Politecnico di Torino

      Users’ behavior in immersive movies

      Virtual Reality (VR) has grown since the first system for entertainment became available on the market. However, the production of movies leveraging this new medium is still in an early exploratory phase. The main reason is that the cinematographic language in VR is still under development, and it is still necessary to learn how to tell stories effectively. A key issue is that VR content creators do not have ...
    • Thesis at Politecnico di Torino

      Automatic generation of character animations and their description

      This proposal can be tackled through more than one thesis works. In fact, the goal is manyfold. On the one side, the idea is to design and develop a system capable to read and understand the description of a scene in a book, a movie script, etc. (in terms of objects and characters described, their behavior, etc.) and automatically create a 3D virtual representation for it. The system shall be able, for ...

Computer Vision, Visual Analytics and Information Visualization

    • Thesis with an external company

      Fine-grained image recognition and damage detection in the insurance domain

      This project will be carried out in collaboration with a major insurance company. The primary goal of the project is to identify the presence of damages in pictures of personal belongings (such as bikes or sports equipment). A secondary objective is to understand whether the same object (or instance) appears in more than one image, and to match photos acquired before and after the damage occurs. The research ...
    • Thesis with an external company

      Deep learning techniques for vehicle re-identification

      Vehicle Re-Identification (ReID) aims to retrieve images of a query vehicle from a large-scale vehicle database, a task with many applications in smart city and road infrastructure management. Since in many circumstances, the license plates cannot be clearly captured, e.g. due to occlusions, poor lightning conditions or adverse weather, a more challenging, but potentially more robust way to achieve this goal ...
    • Thesis at Politecnico di Torino

      Data augmentation techniques for medical image analysis

      Recent advances in deep learning models have been largely attributed to the quantity and diversity of data gathered in recent years. Data augmentation is a strategy that enables practitioners to significantly increase the diversity of data available for training models, without actually collecting new data. Data augmentation techniques such as cropping, padding, and horizontal flipping are commonly used to ...
    • Thesis at Politecnico di Torino

      Integrating high-level semantics and deep learning for image understanding

      Artificial Intelligence agents are required to learn from their surroundings and to reason about the knowledge that has been learned in order to make decisions. While state-of-the-art deep learning typically uses distributed representations, reasoning is normally useful at a higher level of abstraction. As a result, attempts at combining symbolic AI and neural computation into neural-symbolic systems have been ...
    • Thesis at Politecnico di Torino

      Quantitative analysis of face representations in the digital era

      Multiple thesis projects are available within the context of an EU-funded project dedicated to investigating the meaning of the face in present-day digital cultures following a cross-disciplinary approach and in collaboration with a multidisciplinary team. The project focuses on how users represent their identity in the digital world and in particular on social networks. Other sources of images that may be ...
    • Thesis at Politecnico di Torino

      Computer vision techniques for mobile testing

      Many End-to-End (E2E) testing tools allow developers to create repeatable test scripts that mimic a human user's interaction with the application and evaluate its response. Various paradigms of testing tools have been defined that are differentiated based upon the way the widgets are located on the GUI (e.g., text, images, layout properties). This thesis falls within the visual GUI testing paradigm scope, where ...
    • Thesis at Politecnico di Torino

      Self-supervised techniques for medical image representation learning

      Training deep neural networks require large scale annotated datasets which are often difficult to collect in the medical domain. As a consequence, a plethora of small and very specialized datasets have emerged. The medical domain would extremely benefit from more general purpose models that can be applied to a variety of problems. A possible strategy to overcome this issue is to leverage self-supervised ...
    • Thesis with an external company

      Deep learning techniques for digital mammography analysis

      The present proposal falls within a regional project aiming at developing components for automated reading of mammographic images based on deep learning techniques. During screening, up to four mammographic views are acquired for each exam: the goal of the envisioned system is to predict the probability of the exam being positive / negative. Within this project, multiple thesis projects are available, possibly ...

Miscellaneous

    • Thesis with an external company

      User interface for the generation of general purpose (HW & SW) functional tests

      Supervisors: Fabrizio Lamberti
      The topic of this thesis proposal falls within the context of a collaboration of the GRAINS research group of the Control and Computer Engineering (DAUIN) Department with CREA - COLLAUDI ELETTRONICI AUTOMATIZZATI S.R.L. in Ciriè (TO). The goal is to design and realize an environment for the development of functional tests capable to preserve a neat separation between the specification of the test and the ...
    • Thesis at Politecnico di Torino

      Automatic grading of computer programming assignments

      The goal of this thesis is to develop a system supporting the automatic grading of Java programming assignments. Tools exist already that - for the purpose of assigning a grade - compare a student's outcome with a reference developed by either the teaching staff, or by the same or other student(s). Comparison is often performed using test-based approaches, focusing on success rates and lines of code changed. ...
    • Thesis at Politecnico di Torino

      Blockchain and smart contracts: analysis, search and visualization

      The thesis aims at designing and developing a tool for the analysis of smart contracts deployed on existing blockchain platforms. The objective of the tool is to support the user in the identification of smart contracts' main characteristics (e.g., in terms of application field, type, tasks performed, interactions with other smart contracts, etc.), by also exploiting visualization techniques. The thesis student ...
    • Thesis with an external company

      Web crawling e analisi semantica per il supporto all'innovazione del business

      La capacità di profilazione e classificazione delle aziende in base a offerta, mercati e competenze è uno degli elementi chiave per la valorizzazione di ecosistemi produttivi. La tesi prevede lo sviluppo di algoritmi di web crawling e analisi semantica di testi per estrazione di contenuti e classificazione automatica del profilo di business a partire dai siti web aziendali. Struttura tesi: ...