InAR:Inverse Augmented Reality

TL;DR

This paper introduces InAR, a method for distinguishing real from virtual objects in augmented reality scenes by using structure from motion to reconstruct and separate the objects in 3D.

Contribution

The paper proposes a novel approach leveraging 3D reconstruction to differentiate real and virtual objects in augmented reality environments.

Findings

Real and virtual objects can be separated in 3D reconstructions.

Structure from motion effectively distinguishes real from virtual objects.

The method simplifies inverse augmented reality tasks.

Abstract

Augmented reality is the art to seamlessly fuse virtual objects into real ones. In this short note, we address the opposite problem, the inverse augmented reality, that is, given a perfectly augmented reality scene where human is unable to distinguish real objects from virtual ones, how the machine could help do the job. We show by structure from motion (SFM), a simple 3D reconstruction technique from images in computer vision, the real and virtual objects can be easily separated in the reconstructed 3D scene.