Nicola Dall'Asen's Projects
[ICCV 2019] Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression - Official Implementation
NLU engine for the aiwoz chatbot
A beautiful, simple, clean, and responsive Jekyll theme for academics
Telegram bot to get anime info
Official PyTorch implementation of the paper "Graph-based Generative Face Anonymisation with Pose Preservation" in ICIAP 2021
ArXiv Digest and Personalized Recommendations using Large Language Models
Automatically generate a base16 color set for syntax highlighting based on the colors in an image
Run your own GPTChat Telegram bot, with a single command!
Translation of VIP cheatsheets for Machine Learning Deep Learning, and Artificial Intelligence
Let us control diffusion models!
Nightly release of ControlNet 1.1
Evoluzione del coronavirus nella provincia di Belluno, aggiornata ogni giorno con dati ufficiali presi da Azienda Zero.
DeepSeek-VL: Towards Real-World Vision-Language Understanding
A scaffold application to provide a set of API in Deno to interact with a MongoDB database.
Tackling the Generative Learning Trilemma with Denoising Diffusion GANs https://arxiv.org/abs/2112.07804
This is the source code for the animations in the series "Visualizing Deep Learning"
Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann.
Calculate coauthorship distance using data extracted from Google Scholar
A simple API system on a pg database, using knex and objection to simplify connection and management
Unofficial PyTorch Implementation for FaceShifter (https://arxiv.org/abs/1912.13457)
This project provides an official implementation of our recent work on real-time multi-object tracking in videos. The previous works conduct object detection and tracking with two separate models so they are very slow. In contrast, we propose a one-stage solution which does detection and tracking with a single network by elegantly solving the alignment problem. The resulting approach achieves groundbreaking results in terms of both accuracy and speed: (1) it ranks first among all the trackers on the MOT challenges; (2) it is significantly faster than the previous state-of-the-arts. In addition, it scales gracefully to handle a large number of objects.
:books: Freely available programming books
Unofficial PyTorch Implementation for HifiFace (https://arxiv.org/abs/2106.09965)