Argomenti di tesi proposti dal docente.
Ultime tesi seguite dal docente
Tesi di Laurea
- Creazione di un dataset per l'addestramento e la validazione di reti neurali per il completamento automatico di crani
- Creazione di un dataset tramite smart glasses per l'addestramento di Neural Radiance Fields
- Realizzazione di un'interfaccia web per la valutazione della coerenza tra forme 3D e descrizioni testuali
Tesi di Laurea Magistrale
- A Comprehensive Benchmark of Efficient Text-Driven 3D Generative Models
- Additive decomposition of one-dimensional signals using Transformers
- Alignment of Implicit Neural Representations of 3D Shapes via Permutation Symmetries
- An Experimental Study on Generalization in Deep Fake Image Detection
- Automatic detection and classification of products on supermarket shelves
- Ball tracking in Padel Videos using Convolutional Neural Networks
- Canonical orientation and segmentation of CT scans of skulls via 3D neural networks
- Consistent 6D pose estimation via geometry-guided object pose graph construction
- Convolutional Neural Network Architectures for Template Matching
- Corrosion prediction for the automotive industry
- Deep Learning on Neural Radiance Fields
- Deepfake recognition for robust face verification
- Depth Estimation in Stereo Biomedical Images via Proxy-Supervised Deep Learning
- Diffusion Inpainting with Parameter Efficient Learning for the Generation of Architectural Elements
- Empowering Insurance Fraud Investigations: Image Tampering Detection Strategies and Tools
- Enhancing a Text-Shape Coherence Metric by Leveraging Contrastive Losses and a Large-Scale Dataset
- Exploiting and Benchmarking Hardware Acceleration for Computer Vision on Industrial Embedded Devices
- Exploring robustness to viewpoint changes by creating a dataset of simulated dashcam videos
- Generation of Microwave Images for Sensitive Applications with Diffusion Models
- Generative Adversarial Networks for three-dimensional multi-channel virtual fluorescent staining
- Instance Segmentation of Catheters in Chest X-ray Images
- Learning Color Enhancement for Millions of Users
- Mining techniques for self-supervised visual contrastive learning
- Mitigating the effects of Severe Imbalance in Multi-class Semantic Segmentation
- Multi-Grained Attention over Query-Scoring for Dialogue-to-Video Retrieval
- Multi-Task Reconstruction Strategies for Unsupervised 3D Domain Adaptation
- Neural Radiance Fields for Relighting and View Synthesis
- Physically feasible Semantic Segmentation
- Predicting human movement from neural multivariate time series with ResNet
- Reducing Memorization in Latent Diffusion Models for 3D Medical Images Generation
- SkinScan - Recognition of pigmented skin lesions with Vision Transformers and Bayesian Networks
- Super Resolution of DeepFakes for Efficient Identity Swapping
- Towards automatic photo book creation from uncurated photo collections
