Search Results for author: Yuanpeng Liu

Found 4 papers, 0 papers with code

SO(3)-Pose: SO(3)-Equivariance Learning for 6D Object Pose Estimation

no code implementations17 Aug 2022 Haoran Pan, Jun Zhou, Yuanpeng Liu, Xuequan Lu, Weiming Wang, Xuefeng Yan, Mingqiang Wei

The SO(3)-equivariant features communicate with RGB features to deduce the (missed) geometry for detecting keypoints of an object with the reflective surface from the depth channel.

6D Pose Estimation 6D Pose Estimation using RGB +2

Automatic CT Segmentation from Bounding Box Annotations using Convolutional Neural Networks

no code implementations29 May 2021 Yuanpeng Liu, Qinglei Hui, Zhiyi Peng, Shaolin Gong, Dexing Kong

Existing automatic segmentation methods are mainly based on fully supervised learning and have an extremely high demand for precise annotations, which are very costly and time-consuming to obtain.

Clustering Segmentation +1

3DPVNet: Patch-level 3D Hough Voting Network for 6D Pose Estimation

no code implementations15 Sep 2020 Yuanpeng Liu, Jun Zhou, Yuqi Zhang, Chao Ding, Jun Wang

To address the problem, a novel 3DPVNet is presented in this work, which utilizes 3D local patches to vote for the object 6D poses.

6D Pose Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.