no code implementations • 22 Feb 2022 • Hongtao Wu, Jikai Ye, Xin Meng, Chris Paxton, Gregory Chirikjian
We propose a visual foresight model for pick-and-place rearrangement manipulation which is able to learn efficiently.
no code implementations • 12 Aug 2021 • Hongtao Wu, Xin Meng, Sipu Ruan, Gregory Chirikjian
Results show that our method enables the robot to autonomously seat the teddy bear on the 12 previously unseen chairs with a very high success rate.
no code implementations • ICCV 2021 • Yawei Li, He Chen, Zhaopeng Cui, Radu Timofte, Marc Pollefeys, Gregory Chirikjian, Luc van Gool
In this paper, we aim at improving the computational efficiency of graph convolutional networks (GCNs) for learning on point clouds.
1 code implementation • ICCV 2021 • Weixiao Liu, Hongtao Wu, Gregory Chirikjian
In this paper, we propose a novel method called CPD with Local Surface Geometry (LSG-CPD) for rigid point cloud registration.
no code implementations • 1 Jan 2021 • Yawei Li, He Chen, Zhaopeng Cui, Radu Timofte, Marc Pollefeys, Gregory Chirikjian, Luc van Gool
State-of-the-art GCNs adopt $K$-nearest neighbor (KNN) searches for local feature aggregation and feature extraction operations from layer to layer.
1 code implementation • ECCV 2020 • He Chen, Pengfei Guo, Pengfei Li, Gim Hee Lee, Gregory Chirikjian
In this paper, we depart from the multi-person 3D pose estimation formulation, and instead reformulate it as crowd pose estimation.
Ranked #12 on 3D Multi-Person Pose Estimation on Panoptic (using extra training data)
3D Multi-Person Human Pose Estimation 3D Multi-Person Pose Estimation +2