Name: Gianluca Scarpellini
Type: User
Company: @google-deepmind @iit-pavis
Bio: PhD student and former DeepMind intern. Working on robotics exploration and Diffusion Models
Twitter: gianscarpellini
Location: Genoa, Italy
Blog: https://blog.scarpellini.dev
Gianluca Scarpellini's Projects
Tools for manipulating .aedat files (timestamped address-event data from neuromorphic hardware), in Matlab and Python
An open source framework for research in Embodied-AI from AI2.
My Bachelor thesis (in Italian)
HMM and FHMM for Bach Chorals dataset
COCO Stuff API
My solutions for Szeliski's "Computer Vision: Algorithms and Applications"
My solutions (with comments) of C++ Primer - 5th edition
Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks.
A Docker image for PyTorch
Code for "Lifting Monocular Events to 3D Human Poses" - CVPRw 2021
AboutMe
Join the GitHub Graduation Yearbook and "walk the stage" on June 11.
A modular high-level library to train embodied AI agents across a variety of tasks, environments, and simulators.
My notes and implementations from "Haskell from first principle"
My kaggle works
Open Source Differentiable Computer Vision Library for PyTorch
Collection of tasks for fast prototyping, baselining, finetuning and solving problems with deep learning.
MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.
Machine learning metrics for distributed, scalable PyTorch applications.
Self-contained, minimalistic implementation of diffusion models with Pytorch.
Code for Noisy Student Training. https://arxiv.org/abs/1911.04252
A carefully crafted Org exporter back-end for Hugo
Code for "Positional Diffusion: Ordering Unordered Sets with Diffusion Probabilistic Models"