DC-GNet: Deep Mesh Relation Capturing Graph Convolution Network for 3D Human Shape Reconstruction

no code implementations • 27 Aug 2021 • Shihao Zhou, Mengxi Jiang, Shanshan Cai, Yunqi Lei

Previous vertex-level and parameter regression approaches reconstruct 3D human shape based on a pre-defined adjacency matrix to encode positive relations between nodes.

3D Human Shape Estimation Relation

Towards Locality Similarity Preserving to 3D Human Pose Estimation

no code implementations • Asian Conference on Computer Vision Workshops 2020 • Shihao Zhou, Mengxi Jiang, Qicong Wang, Yunqi Lei

Then, to recover the 3D pose from these 2D body parts, we recombine a 3D pose by using 3D body parts that are split from the 3D pose candidates.

3D Human Pose Estimation 3D Pose Estimation

SK-Net: Deep Learning on Point Cloud via End-to-end Discovery of Spatial Keypoints

1 code implementation • 31 Mar 2020 • Weikun Wu, Yan Zhang, David Wang, Yunqi Lei

However, existing point-based methods usually are not adequate to extract the local features and the spatial pattern of a point cloud for further shape understanding.

Joint Representation of Multiple Geometric Priors via a Shape Decomposition Model for Single Monocular 3D Pose Estimation

no code implementations • 31 May 2019 • Mengxi Jiang, Zhuliang Yu, Cuihua Li, Yunqi Lei

Specifically, we propose a Shape Decomposition Model (SDM) in which a 3D pose is considered as the superposition of two parts which are global structure together with some deformations.

3D Pose Estimation Dictionary Learning