Unleashing the digital Michelangelo from your smartphone

July 13, 2023

Until recently, 3D surface reconstruction has been a relatively slow, painstaking process involving significant trial and error and manual input. Its creators claim that the aptly named Neuralangelo does just that through the power of neural networks—and with submillimeter accuracy. His goal was not only to enhance existing 3D reconstruction techniques but also to make them accessible to anyone with a smartphone. Instead of increasing human effort, the Neuralangelo team addressed the root of the problem, opting to use numerical gradients in their multi-resolution hash grid representation, which significantly improved the algorithm's reconstruction quality. "The Computer Science Department's combination of theoretical foundation and hands-on experience prepared me to understand and tackle research challenges," he says.

The source of this news is from Johns Hopkins University