Automatic 3D face reconstruction from single images or video

Breuer, Pia; Kim, Kwang-In; Kienzle, Wolf; Schölkopf, Bernhard; Blanz, Volker

doi:10.1109/afgr.2008.4813339

Cited by 35 publications

(31 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, whereas [5] relied on manual marking of several facial feature points, we automatically detect an initial set of facial feature points that ensure good initialization for the 2D model parameters. Breuer et al [6] present a method for automatically fitting the 3D Morphable Model, but it has a high failure rate and high computational cost.…”

Section: Related Researchmentioning

confidence: 99%

Fully automatic pose-invariant face recognition via 3D pose normalization

Asthana

Marks

Jones

et al. 2011

2011 International Conference on Computer Vision

195

168

View full text Add to dashboard Cite

An ideal approach to the problem of pose-invariant face recognition would handle continuous pose variations, would not be database specific, and would achieve high accuracy without any manual intervention. Most of the existing approaches fail to match one or more of these goals. In this paper, we present a fully automatic system for pose-invariant face recognition that not only meets these requirements but also outperforms other comparable methods. We propose a 3D pose normalization method that is completely automatic and leverages the accurate 2D facial feature points found by the system. The current system can handle 3D pose variation up to +-45 in yaw and +-30 in pitch angles. Recognition experiments were conducted on the USF 3D, Multi-PIE, CMU-PIE, FERET, and FacePix databases. Our system not only shows excellent generalization by achieving high accuracy on all 5 databases but also outperforms other methods convincingly. International Conference on Computer Vision (ICCV)This work may not be copied or reproduced in whole or in part for any commercial purpose. Permission to copy in whole or in part without payment of fee is granted for nonprofit educational and research purposes provided that all such whole or partial copies include the following: a notice that such copying is by permission of Mitsubishi Electric Research Laboratories, Inc.; an acknowledgment of the authors and individual contributions to the work; and all applicable portions of the copyright notice. Copying, reproduction, or republishing for any other purpose shall require a license with payment of fee to Mitsubishi Electric Research Laboratories, Inc. All rights reserved. AbstractAn ideal approach to the problem of pose-invariant face recognition would handle continuous pose variations, would not be database specific, and would achieve high accuracy without any manual intervention. Most of the existing approaches fail to match one or more of these goals. In this paper, we present a fully automatic system for poseinvariant face recognition that not only meets these requirements but also outperforms other comparable methods. We propose a 3D pose normalization method that is completely automatic and leverages the accurate 2D facial feature points found by the system. The current system can handle 3D pose variation up to ±45• in yaw and ±30• in pitch angles. Recognition experiments were conducted on the USF 3D, Multi-PIE, CMU-PIE, FERET, and FacePix databases. Our system not only shows excellent generalization by achieving high accuracy on all 5 databases but also outperforms other methods convincingly.

show abstract

Section: Related Researchmentioning

confidence: 99%

Fully automatic pose-invariant face recognition via 3D pose normalization

Asthana

Marks

Jones

et al. 2011

2011 International Conference on Computer Vision

195

168

View full text Add to dashboard Cite

show abstract

“…Given the linear 3DMM coefficients for shape and texture of the entire face and the facial regions (eyes, nose, mouth and surrounding area), which are concatenated into coefficient vectors c, the algorithm finds the individual from the gallery set with a minimum distance, measured in terms of a cosine criterion d = c1,c2 c1 · c2 (see [1,3]). For each probe image, a comparison with the other two images of that person and with all three images of all 99 other individuals is performed.…”

Section: Resultsmentioning

confidence: 99%

“…To test the new algorithm in a real world scenario we chose the feature detector of [3] to automatically detect the feature positions on the 300 faces taken from the FRGC database. Performing a rank 1 identification experiment again the standard algorithm delivers a recognition rate of 29.6% and the new algorithm yields a recognition rate of 39.0%.…”

Section: Resultsmentioning

confidence: 99%

“…The resulting feature locations can be used to initialize a 3DMM fitting procedure. [3] use SVM for detecting faces, estimating pose angles and finding facial features. From a number of nose point candidates, a model-based criterion selects the most plausible position.…”

Section: Related Workmentioning

confidence: 99%

“…While early work has started from a coarse alignment [2], later versions have relied on manually defined feature point positions [1]. Recently, a fully automated 3DMM fitting algorithm has been presented [3] which uses Support Vector Machines (SVM) for the detection of faces and facial features. However, the quality of the fit turned out to depend critically on the precision of the facial features.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Self-Adapting Feature Layers

Breuer

Blanz

2010

Computer Vision – ECCV 2010

Self Cite

View full text Add to dashboard Cite

Abstract. This paper presents a new approach for fitting a 3D morphable model to images of faces, using self-adapting feature layers (SAFL). The algorithm integrates feature detection into an iterative analysis-bysynthesis framework, combining the robustness of feature search with the flexibility of model fitting. Templates for facial features are created and updated while the fitting algorithm converges, so the templates adapt to the pose, illumination, shape and texture of the individual face. Unlike most existing feature-based methods, the algorithm does not search for the image locations with maximum response, which may be prone to errors, but forms a tradeoff between feature likeness, global feature configuration and image reconstruction error. The benefit of the proposed method is an increased robustness of model fitting with respect to errors in the initial feature point positions. Such residual errors are a problem when feature detection and model fitting are combined to form a fully automated face reconstruction or recognition system. We analyze the robustness in a face recognition scenario on images from two databases: FRGC and FERET.

show abstract

Interactive model‐based reconstruction of the human head using an RGB‐D sensor

Zollhöfer

Thies

Colaianni

et al. 2014

Computer Animation & Virtual

View full text Add to dashboard Cite

We present a novel method for the interactive markerless reconstruction of human heads using a single commodity RGB‐D sensor. Our entire reconstruction pipeline is implemented on the graphics processing unit and allows to obtain high‐quality reconstructions of the human head using an interactive and intuitive reconstruction paradigm. The core of our method is a fast graphics processing unit‐based nonlinear quasi‐Newton solver that allows us to leverage all information of the RGB‐D stream and fit a statistical head model to the observations at interactive frame rates. By jointly solving for shape, albedo and illumination parameters, we are able to reconstruct high‐quality models including illumination corrected textures. All obtained reconstructions have a common topology and can be directly used as assets for games, films and various virtual reality applications. We show motion retargeting, retexturing and relighting examples. The accuracy of the presented algorithm is evaluated by a comparison against ground truth data. Copyright © 2014 John Wiley & Sons, Ltd.

show abstract

Automatic 3D face reconstruction from single images or video

Cited by 35 publications

References 20 publications

Fully automatic pose-invariant face recognition via 3D pose normalization

Fully automatic pose-invariant face recognition via 3D pose normalization

Self-Adapting Feature Layers

Interactive model‐based reconstruction of the human head using an RGB‐D sensor

Contact Info

Product

Resources

About