Dreamland: Controllable World Creation with Simulator and Generative Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mo, Sicheng, Leng, Ziyang, Liu, Leon, Wang, Weizhen, He, Honglin, Zhou, Bolei
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915333942542336
author Mo, Sicheng
Leng, Ziyang
Liu, Leon
Wang, Weizhen
He, Honglin
Zhou, Bolei
author_facet Mo, Sicheng
Leng, Ziyang
Liu, Leon
Wang, Weizhen
He, Honglin
Zhou, Bolei
contents Large-scale video generative models can synthesize diverse and realistic visual content for dynamic world creation, but they often lack element-wise controllability, hindering their use in editing scenes and training embodied AI agents. We propose Dreamland, a hybrid world generation framework combining the granular control of a physics-based simulator and the photorealistic content output of large-scale pretrained generative models. In particular, we design a layered world abstraction that encodes both pixel-level and object-level semantics and geometry as an intermediate representation to bridge the simulator and the generative model. This approach enhances controllability, minimizes adaptation cost through early alignment with real-world distributions, and supports off-the-shelf use of existing and future pretrained generative models. We further construct a D3Sim dataset to facilitate the training and evaluation of hybrid generation pipelines. Experiments demonstrate that Dreamland outperforms existing baselines with 50.8% improved image quality, 17.9% stronger controllability, and has great potential to enhance embodied agent training. Code and data will be made available.
format Preprint
id arxiv_https___arxiv_org_abs_2506_08006
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dreamland: Controllable World Creation with Simulator and Generative Models
Mo, Sicheng
Leng, Ziyang
Liu, Leon
Wang, Weizhen
He, Honglin
Zhou, Bolei
Computer Vision and Pattern Recognition
Large-scale video generative models can synthesize diverse and realistic visual content for dynamic world creation, but they often lack element-wise controllability, hindering their use in editing scenes and training embodied AI agents. We propose Dreamland, a hybrid world generation framework combining the granular control of a physics-based simulator and the photorealistic content output of large-scale pretrained generative models. In particular, we design a layered world abstraction that encodes both pixel-level and object-level semantics and geometry as an intermediate representation to bridge the simulator and the generative model. This approach enhances controllability, minimizes adaptation cost through early alignment with real-world distributions, and supports off-the-shelf use of existing and future pretrained generative models. We further construct a D3Sim dataset to facilitate the training and evaluation of hybrid generation pipelines. Experiments demonstrate that Dreamland outperforms existing baselines with 50.8% improved image quality, 17.9% stronger controllability, and has great potential to enhance embodied agent training. Code and data will be made available.
title Dreamland: Controllable World Creation with Simulator and Generative Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.08006