12 papers
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU
Fan Jiang, Zhaoxu Sun, Mengchao Wang +38
We present ABot-World-0, an action-conditioned video world model for real-time, long-horizon closed-loop interaction, supported by a multi-source data infrastructure spanning AAA g…
Lifting Unlabeled Internet-level Data for 3D Scene Understanding
Yixin Chen, Yaowei Zhang, Huangyue Yu +9
Annotated 3D scene data is scarce and expensive to acquire, while abundant unlabeled videos are readily available on the internet. In this paper, we demonstrate that carefully desi…
G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior
Junfeng Ni, Yixin Chen, Zhifei Yang +4
Despite recent advances in leveraging generative prior from pre-trained diffusion models for 3D scene reconstruction, existing methods still face two critical limitations. First, d…
Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields
Shiqian Li, Ruihong Shen, Junfeng Ni +3
Predicting physical dynamics from raw visual data remains a major challenge in AI. While recent video generation models have achieved impressive visual quality, they still cannot c…
3D Scene Change Modeling With Consistent Multi-View Aggregation
Zirui Zhou, Junfeng Ni, Shujie Zhang +2
Change detection plays a vital role in scene monitoring, exploration, and continual reconstruction. Existing 3D change detection methods often exhibit spatial inconsistency in the…
VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Video
Yu Liu, Baoxiong Jia, Ruijie Lu +5
Building digital twins of articulated objects from monocular video presents an essential challenge in computer vision, which requires simultaneous reconstruction of object geometry…