OriNet: A Fully Convolutional Network for 3D Human Pose Estimation
This addresses pose estimation for computer vision applications, but it appears incremental as it builds on existing methods with a novel representation.
The paper tackled 3D human pose estimation from monocular images by using limb orientations as a new representation, achieving good results on large-scale benchmarks without additional constraints.
In this paper, we propose a fully convolutional network for 3D human pose estimation from monocular images. We use limb orientations as a new way to represent 3D poses and bind the orientation together with the bounding box of each limb region to better associate images and predictions. The 3D orientations are modeled jointly with 2D keypoint detections. Without additional constraints, this simple method can achieve good results on several large-scale benchmarks. Further experiments show that our method can generalize well to novel scenes and is robust to inaccurate bounding boxes.