DeepAI AI Chat
Log In Sign Up

Deep Kinematic Pose Regression

by   Xingyi Zhou, et al.
Tongji University
FUDAN University

Learning articulated object pose is inherently difficult because the pose is high dimensional but has many structural constraints. Most existing work do not model such constraints and does not guarantee the geometric validity of their pose estimation, therefore requiring a post-processing to recover the correct geometry if desired, which is cumbersome and sub-optimal. In this work, we propose to directly embed a kinematic object model into the deep neutral network learning for general articulated object pose estimation. The kinematic function is defined on the appropriately parameterized object motion variables. It is differentiable and can be used in the gradient descent based optimization in network training. The prior knowledge on the object geometric model is fully exploited and the structure is guaranteed to be valid. We show convincing experiment results on a toy example and the 3D human pose estimation problem. For the latter we achieve state-of-the-art result on Human3.6M dataset.


page 8

page 13


Model-based Deep Hand Pose Estimation

Previous learning based hand pose estimation methods does not fully expl...

RePose: Learning Deep Kinematic Priors for Fast Human Pose Estimation

We propose a novel efficient and lightweight model for human pose estima...

Pose Estimation from a Single Depth Image for Arbitrary Kinematic Skeletons

We present a method for estimating pose information from a single depth ...

Pose Trainer: Correcting Exercise Posture using Pose Estimation

Fitness exercises are very beneficial to personal health and fitness; ho...

Mass Displacement Networks

Despite the large improvements in performance attained by using deep lea...