Back to the Future: Joint Aware Temporal Deep Learning 3D Human Pose Estimation
This work addresses the problem of improving accuracy and motion smoothness in 3D human pose estimation for computer vision applications, representing an incremental advancement.
The paper tackles 3D human pose estimation from video by proposing a deep learning network with a deeper CNN channel filter and constraint losses, achieving a new state-of-the-art with reductions in mean per-joint position error by 1%, velocity error by 7%, and acceleration error by 13% on the Human 3.6M benchmark.
We propose a new deep learning network that introduces a deeper CNN channel filter and constraints as losses to reduce joint position and motion errors for 3D video human body pose estimation. Our model outperforms the previous best result from the literature based on mean per-joint position error, velocity error, and acceleration errors on the Human 3.6M benchmark corresponding to a new state-of-the-art mean error reduction in all protocols and motion metrics. Mean per joint error is reduced by 1%, velocity error by 7% and acceleration by 13% compared to the best results from the literature. Our contribution increasing positional accuracy and motion smoothness in video can be integrated with future end to end networks without increasing network complexity. Our model and code are available at https://vnmr.github.io/ Keywords: 3D, human, image, pose, action, detection, object, video, visual, supervised, joint, kinematic