Author: Luca Arrotta

Luca Arrotta
17 POSTS0 COMMENTS
Luca is Ph.D. student at the Department of Computer Science of the University of Milan. His interests are Machine Learning, Data Analysis, IoT, Mobile Programming, and Indoor Positioning. His research currently focuses on Pervasive Computing, Context-awareness, Explainable AI, and Human Activity Recognition in smart environments.

Researchers at Tencent Propose GFP-GAN that Leverages Rich and Diverse Priors Encapsulated in a Pretrained Face GAN for Blind Face Restoration

AI Paper Summary
The goal of blind face restoration is to recover high-quality images of human faces from their low-quality counterparts that have been degraded for an...

PeRFception: A Pipeline of Generating Large-Scale 3D Datasets with Radiance Fields

AI Paper Summary
Implicit representations of 3D scenes can encode hundreds of high-resolution images in a compact format, allowing several applications like 3D reconstruction and photorealistic synthesis...

3 Machine Learning Business Challenges Rooted in Data Sensitivity 

AI Governance
Machine Learning (ML) and, in particular, Deep Learning is drastically changing the way we conduct business as now data can be utilized to guide...

Max Plank Researchers Propose A Metrical Face Shape Predictor Called MICA (MetrIC fAce)

AI Paper Summary
The 3D reconstruction of human faces is an essential building block of several Augmented Reality (AR) and Virtual Reality (VR) applications. Most of the...

Alibaba AI Research Team Introduces ‘DCT-Net’; A Novel Image Translation Architecture For Few-Shot Portrait Stylization

AI Paper Summary
Portrait stylization aims to transform a person's appearance into more creative visual styles (e.g., 3D-cartoon, anime, and hand-drawn) while maintaining personal identity. This research...

NTU Researchers Propose ‘AvatarCLIP’: A Novel Zero-Shot Text-Driven 3D Avatar Generation And Animation Pipeline

AI Paper Summary
The creation of 3D digital avatars is crucial for several industries, ranging from movies to videogames. However, the whole production process is often affordable...

Tsinghua University AI Researchers Propose 9B-Parameter Transformer ‘CogVideo’, Trained By Inheriting A Pretrained text-to-image model, CogView2

AI Paper Summary
This Article is written as a summay by Marktechpost Research Staff based on the paper 'CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers'. All Credit...

Researchers From Trinity College Dublin Propose ‘WasteNet’: A Waste Classification Model Based On Convolutional Neural Networks

AI Paper Summary
Climate change is one of the biggest challenges of our time. Waste recycling is a crucial process that helps mitigate this problem in two...

“Doodle It Yourself” DIY-FSCIL: A Novel AI Framework For Few Shot Class Incremental Learning Without Violating The Data Privacy And Ethical Norms

AI Paper Summary
This summary article is based on the paper 'Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches' and all credit goes to...

Researchers From the University of Hamburg Propose A Machine Learning Model, Called ‘LipSound2’, That Directly Predicts Speech Representations From Raw Pixels

AI Paper Summary
The purpose of the paper presented in this article is to reconstruct speech only based on sequences of images of talking people. The generation...

Researchers from China Analyzed Open Challenges About The Metaverse and Proposed a Blockchain-Based Three-Layer Architecture to Connect the Physical and the Virtual Worlds

AI Paper Summary
In the last few months, there has been a huge hype for the Metaverse, the 3D virtual space in which the users, through their...

Researchers Introduce A Novel Human-Like Driving And Decision Making Framework Designed For Autonomous Vehicles (AVs)

AI Paper Summary
In the last years, we assisted to a great hype around autonomous vehicles (AVs). However, if we want to see streets where AVs and...
12Page 1 of 2