3D human pose estimation via human structure-aware fully connected network

Existing 3D human pose estimation (3D-HPE) methods focus on reducing the overall joint error, resulting in endpoints and bone lengths with large errors. To address this issue, we propose a human structure-aware network, which is capable of recovering 3D joint locations from given 2D joint detections. We cascade a refinement network with a basic network in a residual learning manner, meanwhile fuse the features from 2D and 3D coordinates by a residual connection. Specifically, our refinement network employs a dual-channel structure, in which the symmetrical endpoints are divided into two parts and refined separately. Such a structure is able to avoid the mutual interference of joints with large errors to promise reliable 3D features. Experimental results on the Human3.6M dataset demonstrate that our network reduces the errors of both endpoints and bone lengths compared with existing state-of-the-art approaches.