Video2MR: Automatically Generating Mixed Reality 3D Instructions by Augmenting Extracted Motion from 2D Videos

Video2MR: Automatically Generating Mixed Reality 3D Instructions by Augmenting Extracted Motion from 2D Videos

Keiichi Ihara, Kyzyl Monteiro, Mehrad Faridan, Rubaiat Habib Kazi, Ryo Suzuki  

The ACM International Conference on Intelligent User Interfaces (IUI 2025)

Links:     PDF   Video   ACM DL   arXiv


Abstract

Video2MR automatically transforms 2D instructional videos into mixed-reality 3D sports and exercise guidance. It extracts motion into an avatar and augments that motion with posture comparison, trajectory visualization, time manipulation, and spatial repositioning.

Publication

Keiichi Ihara, Kyzyl Monteiro, Mehrad Faridan, Rubaiat Habib Kazi, and Ryo Suzuki. 2025. Video2MR: Automatically Generating Mixed Reality 3D Instructions by Augmenting Extracted Motion from 2D Videos. Proceedings of the 30th International Conference on Intelligent User Interfaces. ACM, New York, NY, USA.
DOI: https://doi.org/10.1145/3708359.3712159


Slide

coming soon