3D-printed concrete could help buildings absorb carbon instead of releasing it

Led by Professor Masoud Akbarzadeh, the Penn group has developed Diamanti, a 3D-printed structural system that uses both geometry and material science to turn concrete into ...
IEEE

A Multichannel Hybrid 2D–3D-CNN for Hyperspectral Image Classification With Small Training Sample Sizes

Abstract: This article presents an innovative multichannel hybrid 2D–3D-convolutional neural network (MH-2D-3D-CNN) model specifically designed for the challenging task of hyperspectral image ...
Stars and Stripes

Yokota airman’s 3D printing project could reshape engine repair training

Tech. Sgt. Tylar Cravens will pitch his idea for 3D-printed training engine parts to Pentagon leaders during the Air Force ...
GitHub

SoccerNet-v3D: Leveraging Sports Broadcast Replays for 3D Scene Understanding

Sports video analysis is a key domain in computer vision, enabling detailed spatial understanding through multi-view correspondences. In this work, we introduce SoccerNetv3D and ISSIA-3D, two enhanced ...