8 papers
PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation
Jiahao Zhan, Zizhang Li, Hong-Xing Yu +1
We introduce PerpetualWonder, a hybrid generative simulator that enables long-horizon, action-conditioned 4D scene generation from a single image. Current works fail at this task b…
ART: Articulated Reconstruction Transformer
Zizhang Li, Cheng Zhang, Zhengqin Li +7
We introduce ART, Articulated Reconstruction Transformer -- a category-agnostic, feed-forward model that reconstructs complete 3D articulated objects from only sparse, multi-state…
RealWonder: Real-Time Physical Action-Conditioned Video Generation
Wei Liu, Ziyu Chen, Zizhang Li +3
Current video generation models cannot simulate physical consequences of 3D actions like forces and robotic manipulations, as they lack structural understanding of how actions affe…
WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions
Zizhang Li, Hong-Xing Yu, Wei Liu +4
WonderPlay is a novel framework integrating physics simulation with video generation for generating action-conditioned dynamic 3D scenes from a single image. While prior works are…
Product of Experts for Visual Generation
Yunzhi Zhang, Carson Murtuza-Lanier, Zizhang Li +2
Modern neural models capture rich priors and have complementary knowledge over shared data domains, e.g., images and videos. Integrating diverse knowledge from multiple sources --…
The Scene Language: Representing Scenes with Programs, Words, and Embeddings
Yunzhi Zhang, Zizhang Li, Matt Zhou +2
We introduce the Scene Language, a visual scene representation that concisely and precisely describes the structure, semantics, and identity of visual scenes. It represents a scene…