KBody: Towards general, robust, and aligned monocular whole-body estimation

Abstract

KBody is a method for fitting a low-dimensional body model to an image. It follows a predict-and-optimize approach, relying on data-driven model estimates for the constraints that will be used to solve for the body's parameters. Acknowledging the importance of high quality correspondences, it leverages ``virtual joints" to improve fitting performance, disentangles the optimization between the pose and shape parameters, and integrates asymmetric distance fields to strike a balance in terms of pose and shape capturing capacity, as well as pixel alignment. We also show that generative model inversion offers a strong appearance prior that can be used to complete partial human images and used as a building block for generalized and robust monocular body fitting. Project page: https://zokin.github.io/KBody.

11 pages, 6 figures, 58 supplemental figures, project page https://zokin.github.io/KBody , also posted at with high-res images http://graphics.berkeley.edu/papers/Zioulis-KBT-2023-06