Perceiving Systems, Computer Vision

Realistic Digital Human Characters: Challenges, Models and Algorithms

2024

Ph.D. Thesis

ps


Statistical models for the body, head, and hands are essential in various computer vision tasks. However, popular models like SMPL, MANO, and FLAME produce unrealistic deformations due to inherent flaws in their modeling assumptions and how they are trained, which have become standard practices in constructing models for the body and its parts. This dissertation addresses these limitations by proposing new modeling and training algorithms to improve the realism and generalization of current models. We introduce a new model, STAR (Sparse Trained Articulated Human Body Regressor), which learns a sparse representation of the human body deformations, significantly reducing the number of model parameters compared to models like SMPL. This approach ensures that deformations are spatially localized, leading to more realistic deformations. STAR also incorporates shape-dependent pose deformations, accounting for variations in body shape to enhance overall model accuracy and realism. Additionally, we present a novel federated training algorithm for developing a comprehensive suite of models for the body and its parts. We train an expressive body model, SUPR (Sparse Unified Part-Based Representation), on a federated dataset of full-body scans, including detailed scans of the head, hands, and feet. We then separate SUPR into a full suite of state-of-the-art models for the head, hands, and foot. The new foot model captures complex foot deformations, addressing challenges related to foot shape, pose, and ground contact dynamics. The dissertation concludes by introducing AVATAR (Articulated Virtual Humans Trained By Bayesian Inference From a Single Scan), a novel, data-efficient training algorithm. AVATAR allows the creation of personalized, high-fidelity body models from a single scan by framing model construction as a Bayesian inference problem, thereby enabling training from small-scale datasets while reducing the risk of overfitting. These advancements push the state of the art in human body modeling and training techniques, making them more accessible for broader research and practical applications.

Author(s): Ahmed A. A. Osman
Year: 2024
Month: September

Department(s): Perceiving Systems
Bibtex Type: Ph.D. Thesis (phdthesis)
Paper Type: Thesis

School: University of Tübingen

Degree Type: PhD
Attachments:

BibTex

@phdthesis{Osman:Thesis:2024,
  title = {Realistic Digital Human Characters: Challenges, Models and Algorithms},
  author = {Osman, Ahmed A. A.},
  school = {University of Tübingen},
  month = sep,
  year = {2024},
  doi = {},
  month_numeric = {9}
}