3D-UGCN: A Unified Graph Convolutional Network for Robust 3D Human Pose Estimation from Monocular RGB Images.
Jie ZhaoJianing LiWeihan ChenWentong WangPengfei YuanXu ZhangDeshu PengPublished in: CoRR (2024)
Keyphrases
- convolutional network
- image data
- image database
- input image
- image collections
- image retrieval
- image registration
- image features
- image analysis
- image classification
- convolutional neural networks
- object recognition
- color images
- image matching
- multiresolution
- edge detection
- segmentation algorithm
- keypoints
- spatial information
- feature descriptors