robertofranceschi,Roberto Franceschi,github

Hi, I'm Roberto 👋

🚀 I deal with Computer Vision and Robotics, working on cool multi-view 3D reconstruction projects.

💡 3+ years of hands-on experience in Computer Vision and Machine Learning, specializing in multi-view 3D reconstruction (NeRF, gsplat). Extensive experience in perception, training neural nets for Radar, Lidar, and Camera object detection.

🎓 M.Sc. in Data Science and Engineering @ Politecnico di Torino

🌐 Open to new opportunities in Machine Learning, Computer Vision, and - more broadly - AI and Software Engineering.

📫 How to reach me: LinkedIn

Roberto Franceschi's Projects

classification-on-wine-dataset

Shallow learning analysis, comparison of some basic classifiers on the Wine dataset using Sklearn

default-credit-card-prediction

Analysis and classification using machine learning algorithms on the UCI Default of Credit Card Clients Dataset.

dl-radar-detector-for-complex-automotive-scenarios

DL-RTD: End-to-end CNN Radar Target Detection in Complex Automotive Scenarios

domain-adaptation-on-pacs-dataset

Implementation of Domain adaptation on PACS dataset using a modified version of Alexnet.

examination-timetabling-problem

This project presents a heuristic to solve a simplified version of the examination timetabling problem.

image-classification-techniques

Comparison CNNs (Alexnet, VGG-16, ResNet) for image classification on dataset Caltech-101. Transfer learning and data augmentation applied and compared results with the training from scratch.

incremental-learning-on-cifar100

Reproduction of popular methods for class-incremental learning in image recognition and proposal of a new variant.

lung-cancer-subtyping-using-gans

Implementation Subtype-GAN in PyTorch working on multi-omics data. Unsupervised Image segmentation applied to SVS images.

psnerf

PS-NeRF: Neural Inverse Rendering for Multi-view Photometric Stereo (ECCV 2022)

robertofranceschi.github.io

Use this template if you need a quick developer / data science portfolio! Based on a Minimal Jekyll theme for GitHub Pages.

sentiment-analysis-on-tripadvisor-reviews

Sentiment analysis, analyzing user’s textual reviews, to perform a binary classification task (positive or negative mood). Designed a machine learning pipeline able to achieve an F1 score of 96.7% on unseen reviews.

Recommend Projects