Saved in:
Bibliographic Details
Main Authors: Xie, Linxi, Sun, Lisong C., Neall, Ashley, Wu, Tong, Cai, Shengqu, Wetzstein, Gordon
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.18422
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910028239208448
author Xie, Linxi
Sun, Lisong C.
Neall, Ashley
Wu, Tong
Cai, Shengqu
Wetzstein, Gordon
author_facet Xie, Linxi
Sun, Lisong C.
Neall, Ashley
Wu, Tong
Cai, Shengqu
Wetzstein, Gordon
contents Extended reality (XR) demands generative models that respond to users' tracked real-world motion, yet current video world models accept only coarse control signals such as text or keyboard input, limiting their utility for embodied interaction. We introduce a human-centric video world model that is conditioned on both tracked head pose and joint-level hand poses. For this purpose, we evaluate existing diffusion transformer conditioning strategies and propose an effective mechanism for 3D head and hand control, enabling dexterous hand--object interactions. We train a bidirectional video diffusion model teacher using this strategy and distill it into a causal, interactive system that generates egocentric virtual environments. We evaluate this generated reality system with human subjects and demonstrate improved task performance as well as a significantly higher level of perceived amount of control over the performed actions compared with relevant baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2602_18422
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control
Xie, Linxi
Sun, Lisong C.
Neall, Ashley
Wu, Tong
Cai, Shengqu
Wetzstein, Gordon
Computer Vision and Pattern Recognition
Extended reality (XR) demands generative models that respond to users' tracked real-world motion, yet current video world models accept only coarse control signals such as text or keyboard input, limiting their utility for embodied interaction. We introduce a human-centric video world model that is conditioned on both tracked head pose and joint-level hand poses. For this purpose, we evaluate existing diffusion transformer conditioning strategies and propose an effective mechanism for 3D head and hand control, enabling dexterous hand--object interactions. We train a bidirectional video diffusion model teacher using this strategy and distill it into a causal, interactive system that generates egocentric virtual environments. We evaluate this generated reality system with human subjects and demonstrate improved task performance as well as a significantly higher level of perceived amount of control over the performed actions compared with relevant baselines.
title Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.18422