5 papers
FoLD: Force-Informed Learning for Dexterous Articulated Object Manipulation
Haowei Shen, Tingai Li, Yumeng Liu +6
Transferring human demonstrations to dexterous robots remains challenging because differences in hand morphology and contact dynamics often cause retargeted motions to fail at prod…
Skeletal-Anchored Dual Harmonics for Structured 3D Modeling
Zhentao Huang, Changhao Li, Ruizhen Hu +2
We present Skeletal-Anchored Dual Harmonics (SADH), a novel 3D shape representation that tightly couples local surface geometry with internal meso-skeletal organization. SADH repre…
LoBoFit: Flexible Garment Refitting via Local Bone Mapping Blending
Meng Zhang, Yu Xin, Feiya Guo +3
Garment refitting, the task of adapting a garment from a source to a target avatar, must preserve the original design features and fine-scale wrinkles, a challenge exacerbated by s…
MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generation
Changhao Li, Yu Xin, Xiaowei Zhou +4
We introduce Masked Anchored SpHerical Distances (MASH), a novel multi-view and parametrized representation of 3D shapes. Inspired by multi-view geometry and motivated by the impor…
ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting
Junfu Guo, Yu Xin, Gaoyi Liu +3
We tackle the challenge of concurrent reconstruction at the part level with the RGB appearance and estimation of motion parameters for building digital twins of articulated objects…