← ArchivePaper2010
High-Quality Single-Shot Capture of Facial Geometry
Thabo Beeler, Bernd Bickel, Paul Beardsley, Bob Sumner, Markus Gross
Pore-level facial geometry from a single passive stereo shot, the start of the Medusa capture line at Disney Research.
Abstract
This paper describes a passive stereo system for capturing the 3D geometry of a face in a single-shot under standard light sources. The system is low-cost and easy to deploy. Results are submillimeter accurate and commensurate with those from state-of-the-art systems based on active lighting, and the models meet the quality requirements of a demanding domain like the movie industry. Recovered models are shown for captures from both high-end cameras in a studio setting and from a consumer binocular-stereo camera, demonstrating scalability across a spectrum of camera deployments, and showing the potential for 3D face modeling to move beyond the professional arena and into the emerging consumer market in stereoscopic photography. Our primary technical contribution is a modification of standard stereo refinement methods to capture pore-scale geometry, using a qualitative approach that produces visually realistic results. The second technical contribution is a calibration method suited to face capture systems. The systemic contribution includes multiple demonstrations of system robustness and quality. These include capture in a studio setup, capture off a consumer binocular-stereo camera, scanning of faces of varying gender and ethnicity and age, capture of highly-transient facial expression, and scanning a physical mask to provide ground-truth validation.
How to read this
- Category
- Capture system: single-shot passive facial geometry capture
- Contributions
- A low-cost, easy-to-deploy passive stereo system that captures 3D face geometry in a single shot under standard light sources, with submillimeter accuracy comparable to active-lighting systems
- A modification of standard stereo refinement to recover pore-scale geometry via a qualitative approach producing visually realistic results
- A calibration method suited to face-capture systems, plus demonstrations of robustness and scalability from studio high-end cameras to a consumer binocular-stereo camera
- Context
- The start of Disney Research's Medusa capture line, building toward photoreal digital actors (Alexander et al., The Digital Emily Project) using passive stereo rather than active lighting.Builds on: The Digital Emily Project: Achieving a Photorealistic Digital Actor
- Correctness
- The pore-scale refinement is explicitly a qualitative approach aimed at visual realism, so 'submillimeter' accuracy is the system claim while fine pore detail is plausibility-driven; readers should keep in mind single-shot capture trades the temporal sequences of active rigs for deployment simplicity.
- Clarity
- Accessible; a first pass conveys the single-shot passive-stereo idea and the consumer-vs-studio framing, do a second pass for the stereo-refinement modification and calibration.
- How to read it
- Read the system overview and the single-shot motivation first; a second pass on the pore-scale stereo refinement and calibration is worthwhile if you build or evaluate face scanners.
Related work
- High Resolution Passive Facial Performance Capture 2010 / SIGGRAPH
- Displaced Dynamic Expression Regression for Real-Time Facial Tracking and Animation 2014 / SIGGRAPH
- Face2Face: Real-Time Face Capture and Reenactment of RGB Videos 2016 / CVPR
- High-Quality Face Capture Using Anatomical Muscles 2019 / CVPR
Keywords
This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →