Mixed Reality

Also known as MR

Follow this topic Ask about this topic

Latest papers

9 papers0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

SnapPhysics: A Physics-Aware Scene Graph from a Single View for Interactive Mixed Reality Scenes
Sep 17, 2026Suji Kang, Seok-Young Kim, Young Bin Kim +4Physical Reasoning Mixed Reality
KAIST UVR Lab · VISUS, University of Stuttgart · KAIST UVR Lab KAIST KI-ITC ARRC
Can You Say This for Me? Speaking Up by Proxy in Co-Located Discussion
Aug 22, 2026Yue Shen, Rehema Abulikemu, Ryan P. McMahan +1Mixed Reality
Virginia Tech Department of Computer Science Blacksburg, Virginia, USA
Intuitive Directional Sense Presentation to the Torso Using McKibben-Based Surface Haptic Sensation in Immersive Space
Aug 10, 2026Kenta Yokoe, Tadayoshi Aoyama, Yuki Funabora +2Mixed Reality Haptic Feedback
Department of Micro-Nano Mechanical Science and Engineering, Nagoya University, Nagoya, Aichi, 464-8603, Japan · Department of Mechanical Systems Engineering, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8603, Japan · Center for One Medicine Innovative Translational Research, Gifu University, Yanagido 1-1, Gifu, Gifu 501-1193, Japan +1
FleetScape: A Mixed Reality Sandtable for Spatial Supervision and Control of Scalable Drone Fleets
Jul 29, 2026Peisen Xu, Jérémie Garcia, Peter Cleveland +2Multi-Robot Systems Mixed Reality
CNRS, IPAL, Singapore · University of Toulouse, Fédération ENAC ISAE-SUPAERO ONERA Toulouse, France · National University of Singapore, School of Computing Singapore +2
Applying Deep Learning for cockpit segmentation in the context of mixed reality
Jun 2, 2026Alexandre Leles Sousa, Pedro de Oliveira Nielson, Erick Oliveira Rodrigues +2Image Segmentation Mixed Reality
* Laboratdrio de Robética, sistemas inteligentes e Complezos - RobSIC Instituto de Ciências Tecnoldgicas Universidade Federal de Itajubd, Campus Itabira, MG. · ** Universidade Tecnológica Federal do Parand - UTFPR, Campus Pato Branco/PR
PicoEyes: Unified Gaze Estimation Framework for Mixed Reality with a Large-Scale Multi-View Dataset
May 8, 2026Fuxin Duan, Hui WangGaze Estimation Mixed Reality
Pico, Bytedance
Point & Grasp: Flexible Selection of Out-of-Reach Objects Through Probabilistic Cue Integration
Apr 24, 2026Xuejing Luo, Hee-Seung Moon, Christian Holz +1Mixed Reality
Department of Information and Communication Engineering, School of Electrical Engineering Aalto University Helsinki, Finland ELLIS Institute Helsinki, Finland · School of Computer Science and Engineering Chung-Ang University Seoul, Republic of Korea · ETH Zürich Zurich, Switzerland
Int3DNet: Scene-Motion Cross Attention Network for 3D Intention Prediction in Mixed Reality
Mar 9, 2026Taewook Ha, Woojin Cho, Dooyoung Kim +1Mixed Reality
KAIST UVR Lab · KAIST KI-ITC PMRC · KAIST KI-ITC ARRC
PlayWrite: A Multimodal System for AI Supported Narrative Co-Authoring Through Play in XR
Mar 2, 2026Esen K. Tütüncü, Qian Zhou, Frederik Brudy +2Mixed Reality Interactive Storytelling
Institute of Neurosciences of the University of Barcelona, Barcelona, Spain · Autodesk Research, San Francisco, USA · Autodesk Research, Toronto, Canada

Sep 17, 2026J/K move · Enter open · S save

SnapPhysics: A Physics-Aware Scene Graph from a Single View for Interactive Mixed Reality Scenes

Suji Kang, Seok-Young Kim, Young Bin Kim, Taewook Ha+3

KAIST UVR Lab · VISUS, University of Stuttgart · KAIST UVR Lab KAIST KI-ITC ARRC

Physical Reasoning Mixed Reality 3D SGG

Open paper AskPDF arXiv

We propose SnapPhysics, a training-free framework that reconstructs 3D objects and estimates their physical properties such as mass, friction, and center of gravity from a single image. For physically coherent interactions in mixed reality (MR), such properties are as important as geometry. Prior approaches infer them by analyzing object dynamics in video, which is computationally costly, or by querying vision-language models (VLMs) on single images, which lacks geometric grounding and inter-object relationships. We address these limitations by combining instance-level 3D reconstruction and spatial alignment with a physics-aware scene graph that encodes these relationships and per-object metric geometry as structured context for VLM-based property reasoning. Experiments on 3D-FRONT show that SnapPhysics improves scene-level F-Score by 18.6% over the best learning-based method, and on real captured scenes with ground-truth mass, it reduces the mean absolute log difference error (mALDE) by up to 20.5% and improves log-scale correlation (

r^2_{\mathrm{ls}}

) by up to 19.6% over VLM-only estimation. SnapPhysics enables physically interactive MR experiences without manual parameter tuning. Project page: https://snapphysics-ismar2026.github.io/.