6 papers
Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation
Mutian Xu, Tianbao Zhang, Tianqi Liu +3
Simulating robot-world interactions is a cornerstone of Embodied AI. Recently, a few works have shown promise in leveraging video generations to transcend the rigid visual/physical…
LoFA: Learning to Predict Personalized Priors for Fast Adaptation of Visual Generative Models
Yiming Hao, Mutian Xu, Chongjie Ye +4
Personalizing visual generative models to meet specific user needs has gained increasing attention, yet current methods like Low-Rank Adaptation (LoRA) remain impractical due to th…
VC-Agent: An Interactive Agent for Customized Video Dataset Collection
Yidan Zhang, Mutian Xu, Yiming Hao +6
Facing scaling laws, video data from the internet becomes increasingly important. However, collecting extensive videos that meet specific needs is extremely labor-intensive and tim…
Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion
Mutian Xu, Chongjie Ye, Haolin Liu +3
3D data simulation aims to bridge the gap between simulated and real-captured 3D data, which is a fundamental problem for real-world 3D visual tasks. Most 3D data simulation method…
TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation
Hongxiang Zhao, Xingchen Liu, Mutian Xu +3
We address key limitations in existing datasets and models for task-oriented hand-object interaction video generation, a critical approach of generating video demonstrations for ro…
SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation
Mutian Xu, Xingyilang Yin, Lingteng Qiu +3
We introduce SAMPro3D for zero-shot instance segmentation of 3D scenes. Given the 3D point cloud and multiple posed RGB-D frames of 3D scenes, our approach segments 3D instances by…