임요한

We present a real-time AR system that enables interaction with physical cuboid- and cylinder-shaped objects by representing them as compact superquadrics. Our approach uses Instant Surface Normal (ISN) maps-color images encoding per-pixel geometry-to detect and segment objects based on shape rather than appearance. Superquadric parameters are extracted sequentially, allowing efficient and updatable 3D modeling in real time. Experimental results show accurate detection, consistent segmentation, and reconstruction quality comparable to existing methods, while achieving over 5× faster inference. This system allows physical objects to be seamlessly integrated as interactive elements in dynamic AR environments.

Diminished reality (DR) removes virtual and real objects from the user’s view, decluttering and optimizing what the user sees through augmented/mixed reality. However, removing real objects create a potential safety concern because users may unintentionally bump into the diminished object. To address this issue, we apply characteristics of peripheral vision to DR and diminish objects when they are in the peripheral region and show the object when the user focuses on the object. We created 3 different object opacity control functions that use gaze information and evaluated them.