As a 3D artist on the Aria Digital Twin project, I got to create highly accurate 3D models of furniture, everyday objects and a variety of spaces for the ADT dataset.

Aria Digital Twin is an egocentric dataset captured using Aria glasses, with extensive simulated ground truth for devices, objects and environment.

This dataset sets a new standard for egocentric machine perception research, and accelerates research into a number of challenges including 3D object detection and tracking, scene reconstruction and understanding, sim-to-real learning, human pose prediction, while also inspiring new machine perception tasks for augmented reality (AR) applications.

I was part of a small team of artists, modeling furniture pieces and objects, using photogrammetry to capture textures, cleaning up scans, placing objects into a scene, setting up lighting and producing renders and presentation materials.