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

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Alias-Free Generative Adversarial Networks
• Recovering 3D Human Mesh from Monocular Images: A Survey
• PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images
• Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild
• Deep Portrait Image Completion and Extrapolation
• Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesis
• Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms
• Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery
• Everybody Is Unique: Towards Unbiased Human Mesh Recovery

Cited by in corpus (1)

• Recovering 3D Human Mesh from Monocular Images: A Survey