Building Statistical Shape Spaces for 3D Human Modeling

Abstract

Statistical models of 3D human shape and pose learned from scan databases have developed into valuable tools to solve a variety of vision and graphics problems. Unfortunately, most publicly available models are of limited expressiveness as they were learned on very small databases that hardly reflect the true variety in human body shapes. In this paper, we contribute by rebuilding a widely used statistical body representation from the largest commercially available scan database, and making the resulting model available to the community (visit http://humanshape.mpi-inf.mpg.de). As preprocessing several thousand scans for learning the model is a challenge in itself, we contribute by developing robust best practice solutions for scan alignment that quantitatively lead to the best learned models. We make implementations of these preprocessing steps also publicly available. We extensively evaluate the improved accuracy and generality of our new model, and show its improved performance for human body reconstruction from sparse input data.

Published in Pattern Recognition 2017

References in corpus (1)

• Estimation of Human Body Shape and Posture Under Clothing

Cited by in corpus (22)

• STAR: Sparse Trained Articulated Human Body Regressor
• A bi-atrial statistical shape model for large-scale in silico studies of human atria: model development and application to ECG simulations
• DPFM: Deep Partial Functional Maps
• SoftSMPL: Data-driven Modeling of Nonlinear Soft-tissue Dynamics for Parametric Humans
• Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network
• MedalCare-XL: 16,900 healthy and pathological 12 lead ECGs obtained through electrophysiological simulations
• ZerNet: Convolutional Neural Networks on Arbitrary Surfaces via Zernike Local Tangent Space Estimation
• Detailed, accurate, human shape estimation from clothed 3D scan sequences
• General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues
• Learning Anthropometry from Rendered Humans
• A Neural Anthropometer Learning from Body Dimensions Computed on Human 3D Meshes
• Model-based Outdoor Performance Capture
• Concise and Effective Network for 3D Human Modeling from Orthogonal Silhouettes
• SHARP 2020: The 1st Shape Recovery from Partial Textured 3D Scans Challenge Results
• Local Deep Implicit Functions for 3D Shape
• Latent feature disentanglement for 3D meshes
• Local High-order Regularization on Data Manifolds
• TailorMe: Self-Supervised Learning of an Anatomically Constrained Volumetric Human Shape Model
• Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking
• Learning Compositional Representation for 4D Captures with Neural ODE
• High-Resolution Augmentation for Automatic Template-Based Matching of Human Models
• Multilevel active registration for kinect human body scans: from low quality to high quality