7 papers
GRC-Pose: Generation-Reconstruction Correspondence for Prior-Free 6D Object Pose Tracking
Shiyang Liu, Weiquan Lin, Luping Xiao +4
Prior-free 6D object pose tracking seeks to recover the trajectory of an unseen object from a single RGB video without object-specific CAD models, posed reference images, or pose a…
Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer
Weiquan Lin, Yu Deng, Shiyang Liu +6
Hand-object interaction (HOI) modeling remains challenging because it requires joint reasoning about hand articulation, object geometry, contact, semantics, and dynamics under seve…
HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning
Taowen Wang, Zikang Xie, Bin Yang +13
Humanoid robots promise whole-body interaction in human-centered environments, but scalable policy learning remains difficult because task-level decision-making and whole-body dyna…
ScaleHP: Scale-Mediated Optimization of Coupled Errors for Metric-Space Hand Pose Estimation
Ruitao Jing, Xingyu Chen, Hongyang Li +3
In this paper, we present ScaleHP, a unified framework that explicitly represents per-instance metric scale to resolve the coupled errors in calibrated camera-space hand pose estim…
SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model
Yukai Shi, Weiyu Li, Zihao Wang +4
We propose a decoupled 3D scene generation framework called SceneMaker in this work. Due to the lack of sufficient open-set de-occlusion and pose estimation priors, existing method…
Detect Anything via Next Point Prediction
Qing Jiang, Junan Huo, Xingyu Chen +6
Object detection has long been dominated by traditional coordinate regression-based models, such as YOLO, DETR, and Grounding DINO. Although recent efforts have attempted to levera…
SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features
Jinyuan Qu, Hongyang Li, Xingyu Chen +5
In this paper, we present SegDINO3D, a novel Transformer encoder-decoder framework for 3D instance segmentation. As 3D training data is generally not as sufficient as 2D training i…