AI Generates 3D high-resolution reconstructions of people from 2D images | Introduction to PIFuHD

Author(s): Louis Bouchard

Originally published on Towards AI.

This AI Generates 3D high-resolution reconstructions of people from 2D images! It only needs a single image of you to generate a 3D avatar that looks just like you, even from the back!

The coolest thing about this new paper is that they made a demo available on google colab where you can easily try it on yourself, as I will show in this article! But first, let’s see how they did that.

Researchers at Facebook and the University of Southern California recently introduced a new paper called “PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization”. In short, it uses a 2D image of someone to reconstruct a 3D high-resolution version of the same person. The main goal was to achieve a high-fidelity 3d reconstruction of clothed humans with detailed information such… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI