WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sun, Wenqiang, Zhang, Haiyu, Wang, Haoyuan, Wu, Junta, Wang, Zehan, Wang, Zhenwei, Wang, Yunhong, Zhang, Jun, Wang, Tengfei, Guo, Chunchao
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914204446883840
author Sun, Wenqiang
Zhang, Haiyu
Wang, Haoyuan
Wu, Junta
Wang, Zehan
Wang, Zhenwei
Wang, Yunhong
Zhang, Jun
Wang, Tengfei
Guo, Chunchao
author_facet Sun, Wenqiang
Zhang, Haiyu
Wang, Haoyuan
Wu, Junta
Wang, Zehan
Wang, Zhenwei
Wang, Yunhong
Zhang, Jun
Wang, Tengfei
Guo, Chunchao
contents This paper presents WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off between speed and memory that limits current methods. WorldPlay draws power from three key innovations. 1) We use a Dual Action Representation to enable robust action control in response to the user's keyboard and mouse inputs. 2) To enforce long-term consistency, our Reconstituted Context Memory dynamically rebuilds context from past frames and uses temporal reframing to keep geometrically important but long-past frames accessible, effectively alleviating memory attenuation. 3) We also propose Context Forcing, a novel distillation method designed for memory-aware model. Aligning memory context between the teacher and student preserves the student's capacity to use long-range information, enabling real-time speeds while preventing error drift. Taken together, WorldPlay generates long-horizon streaming 720p video at 24 FPS with superior consistency, comparing favorably with existing techniques and showing strong generalization across diverse scenes. Project page and online demo can be found: https://3d-models.hunyuan.tencent.com/world/ and https://3d.hunyuan.tencent.com/sceneTo3D.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14614
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
Sun, Wenqiang
Zhang, Haiyu
Wang, Haoyuan
Wu, Junta
Wang, Zehan
Wang, Zhenwei
Wang, Yunhong
Zhang, Jun
Wang, Tengfei
Guo, Chunchao
Computer Vision and Pattern Recognition
Graphics
This paper presents WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off between speed and memory that limits current methods. WorldPlay draws power from three key innovations. 1) We use a Dual Action Representation to enable robust action control in response to the user's keyboard and mouse inputs. 2) To enforce long-term consistency, our Reconstituted Context Memory dynamically rebuilds context from past frames and uses temporal reframing to keep geometrically important but long-past frames accessible, effectively alleviating memory attenuation. 3) We also propose Context Forcing, a novel distillation method designed for memory-aware model. Aligning memory context between the teacher and student preserves the student's capacity to use long-range information, enabling real-time speeds while preventing error drift. Taken together, WorldPlay generates long-horizon streaming 720p video at 24 FPS with superior consistency, comparing favorably with existing techniques and showing strong generalization across diverse scenes. Project page and online demo can be found: https://3d-models.hunyuan.tencent.com/world/ and https://3d.hunyuan.tencent.com/sceneTo3D.
title WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2512.14614