English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper presents an inverse kinematic optimization layer (IKOL) for 3Dhuman pose and shape estimation that leverages the strength of bothoptimization- and regression-based methods within an end-to-end framework. IKOLinvolves a nonconvex optimization that establishes an implicit mapping from animage's 3D keypoints and body shapes to the relative body-part rotations. The3D keypoints and the body shapes are the inputs and the relative body-partrotations are the solutions. However, this procedure is implicit and hard tomake differentiable. So, to overcome this issue, we designed a Gauss-Newtondifferentiation (GN-Diff) procedure to differentiate IKOL. GN-Diff iterativelylinearizes the nonconvex objective function to obtain Gauss-Newton directionswith closed form solutions. Then, an automatic differentiation procedure isdirectly applied to generate a Jacobian matrix for end-to-end training.Notably, the GN-Diff procedure works fast because it does not rely on atime-consuming implicit differentiation procedure. The twist rotation and shapeparameters are learned from the neural networks and, as a result, IKOL has amuch lower computational overhead than most existing optimization-basedmethods. Additionally, compared to existing regression-based methods, IKOLprovides a more accurate mesh-image correspondence. This is because ititeratively reduces the distance between the keypoints and also enhances thereliability of the pose structures. Extensive experiments demonstrate thesuperiority of our proposed framework over a wide range of 3D human pose andshape estimation methods.

IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation