18 citations · 18 across the 10 of their papers we have counts for
12 papers
Distilling Dense Trajectory Teachers For Large-Motion Video World Models
Shuofeng Sun, Linqing Zhao, Haibin Yan
Video world models are expected to generate videos that accurately follow specified camera trajectories while maintaining consistent 3D structures. However, existing models are pre…
SceneAE: Scene Generation and Reconstruction in Queryable 3D-Anchored Latent Space
Shuofeng Sun, Wenzhao Zheng, Yunpeng Zhang +3
Recent video world models have increasingly adopted 3D memory mechanisms to integrate historical observations into a lightweight and persistent scene representation. This naturally…
iMaC: Translating Actions into Motion and Contact Images for Embodied World Models
Zhenyu Wu, Xiuwei Xu, Yukun Zhou +8
Embodied world models have emerged as a pivotal paradigm for visual robotic decision-making and interactive environment simulation. However, conventional embodied frameworks rely o…
iGaussian: Real-Time Camera Pose Estimation via Feed-Forward 3D Gaussian Splatting Inversion
Hao Wang, Linqing Zhao, Xiuwei Xu +2
Recent trends in SLAM and visual navigation have embraced 3D Gaussians as the preferred scene representation, highlighting the importance of estimating camera poses from a single i…
MoTo: A Zero-shot Plug-in Interaction-aware Navigation for General Mobile Manipulation
Zhenyu Wu, Angyuan Ma, Xiuwei Xu +5
Mobile manipulation stands as a core challenge in robotics, enabling robots to assist humans across varied tasks and dynamic daily environments. Conventional mobile manipulation ap…
Pseudo Depth Meets Gaussian: A Feed-forward RGB SLAM Baseline
Linqing Zhao, Xiuwei Xu, Yirui Wang +5
Incrementally recovering real-sized 3D geometry from a pose-free RGB stream is a challenging task in 3D reconstruction, requiring minimal assumptions on input data. Existing method…
MoManipVLA: Transferring Vision-language-action Models for General Mobile Manipulation
Zhenyu Wu, Yuheng Zhou, Xiuwei Xu +2
Mobile manipulation is the fundamental challenge for robotics to assist humans with diverse tasks and environments in everyday life. However, conventional mobile manipulation appro…
Embodied Instruction Following in Unknown Environments
Zhenyu Wu, Ziwei Wang, Xiuwei Xu +5
Enabling embodied agents to complete complex human instructions from natural language is crucial to autonomous systems in household services. Conventional methods can only accompli…
Hardness-Aware Scene Synthesis for Semi-Supervised 3D Object Detection
Shuai Zeng, Wenzhao Zheng, Jiwen Lu +1
3D object detection aims to recover the 3D information of concerning objects and serves as the fundamental task of autonomous driving perception. Its performance greatly depends on…
X-3D: Explicit 3D Structure Modeling for Point Cloud Recognition
Shuofeng Sun, Yongming Rao, Jiwen Lu +1
Numerous prior studies predominantly emphasize constructing relation vectors for individual neighborhood points and generating dynamic kernels for each vector and embedding these i…
Anyview: Generalizable Indoor 3D Object Detection with Variable Frames
Zhenyu Wu, Xiuwei Xu, Ziwei Wang +4
In this paper, we propose a novel network framework for indoor 3D object detection to handle variable input frame numbers in practical scenarios. Existing methods only consider fix…
Embodied Task Planning with Large Language Models
Zhenyu Wu, Ziwei Wang, Xiuwei Xu +2
Equipping embodied agents with commonsense is important for robots to successfully complete complex human instructions in general environments. Recent large language models (LLM) c…