3D-UGCN: A Unified Graph Convolutional Network for Robust 3D Human Pose Estimation from Monocular RGB Images
This addresses occlusion in 3D human pose estimation from monocular RGB images, which is important for applications like behavior recognition and human-computer interaction, but appears incremental as it builds on existing UGCN methods.
The paper tackled the problem of missing human posture skeleton sequences in single-view videos for 3D human pose estimation by proposing an improved spatial-temporal graph convolutional network (UGCN), which processes 3D data and improves skeleton sequences to resolve occlusion issues.
Human pose estimation remains a multifaceted challenge in computer vision, pivotal across diverse domains such as behavior recognition, human-computer interaction, and pedestrian tracking. This paper proposes an improved method based on the spatial-temporal graph convolution net-work (UGCN) to address the issue of missing human posture skeleton sequences in single-view videos. We present the improved UGCN, which allows the network to process 3D human pose data and improves the 3D human pose skeleton sequence, thereby resolving the occlusion issue.