SPHEAR: Spherical Head Registration for Complete Statistical 3D Modeling

We present SPHEAR, an accurate, differentiable parametric statistical 3D human head model, enabled by a novel 3D registration method based on spherical embeddings. We shift the paradigm away from the classical Non-Rigid Registration methods, which operate under various surface priors, increasing rec...

Full description

Saved in:
Bibliographic Details
Main Authors: Bazavan, Eduard Gabriel, Zanfir, Andrei, Szente, Teodor Alexandru, Zanfir, Mihai, Alldieck, Thiemo, Sminchisescu, Cristian
Format: Conference Proceeding
Language:English
Subjects:
Rendering (computer graphics)
Semantics
Shape
Skin
Solid modeling
Surface reconstruction
Three-dimensional displays
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present SPHEAR, an accurate, differentiable parametric statistical 3D human head model, enabled by a novel 3D registration method based on spherical embeddings. We shift the paradigm away from the classical Non-Rigid Registration methods, which operate under various surface priors, increasing reconstruction fidelity and minimizing required human intervention. Additionally, SPHEAR is a complete model that allows not only to sample diverse synthetic head shapes and facial expressions, but also gaze directions, high-resolution color textures, surface normal maps, and hair cuts represented in detail, as strands. SP-HEAR can be used for automatic realistic visual data generation, semantic annotation, and general reconstruction tasks. Compared to state-of-the-art approaches, our components are fast and memory efficient, and experiments support the validity of our design choices and the accuracy of registration, reconstruction and generation techniques.
ISSN:2475-7888
DOI:10.1109/3DV62453.2024.00145