Multi-Finger-Based Arbitrary Region-of-Interest Selection in Virtual Reality

Abstract

We present a new 3D user interface for selecting an arbitrarily shaped region of interest (ROI) in virtual reality. The interface’s primary objective is the selection of a surface geometry’s boundaries having various shapes (e.g., arch- or concave-shaped boundaries) for 3D model editing or annotation. Compared with previous convex ROI shape selection, we explore a more challenging arbitrarily shaped selection. We address this issue by generating a flexible selection space based on a user’s multiple finger position mapping into the shaped ROI on a 3D surface geometry and providing visual feedback to assist the user in progressively refining the selection shape. We employ a leap motion controller for free-hand finger position input and gesture-based navigation to construct a flexible and natural user interface. To demonstrate the efficiency of our method, we evaluate the system usability by conducting a user study and compare the results with those of the state-of-the-art manual-input ROI selection technique.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (NRF-2019R1A2C1008244).

Notes on contributors

Qimeng Zhang

Qimeng Zhang received the PhD degree from the Interdisciplinary Program in Visual Information Processing, Korea University, in 2022. Currently, she is a research professor with the BK21 four R&E Center for Computer Science and Engineering, Korea University. Her current research interests include geometry processing, physically-based simulation, and augmented/virtual reality.

Chang-Hun Kim

Chang-Hun Kim is currently a professor in the Department of Computer Science and Engineering at Korea University. His current research interests include fluid simulation and mesh processing and virtual reality.

Hae Won Byun

Hae Won Byun is a professor in the School of AI Convergence at Sungshin Women’s University. Her research focuses on enhancing the functionality of augmented/virtual reality using deep learning.