A Multiresolution 3D Morphable Face Model and Fitting Framework

Huber, Patrik; Hu, Guosheng; Tena, Rafael; Mortazavian, Pouria; Koppen, W. P.; Christmas, William J.; Rätsch, Matthias; Kittler, Josef

doi:10.5220/0005669500790086

Cited by 209 publications

(154 citation statements)

References 15 publications

Supporting

Mentioning

154

Contrasting

Order By: Relevance

“…draw-on-top on Android device [25]) without his/her notice. To generate a 3D face model from captured image/video, the most suitable approach in existing literature is to use pre-built 3D Morphable Models (3DMMs) [26]- [28]. 3DMMs are the statistical 3D representations built on facial textures and shapes of many different subjects (e.g.…”

Section: B Compromising Attacks and Defensesmentioning

confidence: 99%

“…For our experiments, we generated 3D face models from genuine videos of each subject in our dataset by using three different tools: i) Surrey Face Model (labeled as 3D sf in Fig. 2), a multi-resolution 3DMM and accompanying open-source tool [28]; ii) FaceGen 9 (3D f g ), and iii) demo version of CrazyTalk8 10 (3D ct8 ) commercial tools used for 3D printing or rendering 3D animation and game characters. Although the demo tool puts a brand mark on 3D models, they don't seem to have any effect on the effectiveness of the attack.…”

Section: Facial Authentication Systems Studiedmentioning

confidence: 99%

See 1 more Smart Citation

rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System

Uzun¹

2018

Proceedings 2018 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

Abstract-Facial/voice-based authentication is becoming increasingly popular (e.g., already adopted by MasterCard and AliPay), because it is easy to use. In particular, users can now authenticate themselves to online services by using their mobile phone to show themselves performing simple tasks like blinking or smiling in front of its built-in camera. Our study shows that many of the publicly available facial/voice recognition services (e.g. Microsoft Cognitive Services or Amazon Rekognition) are vulnerable to even the most primitive attacks. Furthermore, recent work on modeling a person's face/voice (e.g. Face2Face [1]) allows an adversary to create very authentic video/audio of any target victim to impersonate that target. All it takes to launch such attacks are a few pictures and voice samples of a victim, which can all be obtained by either abusing the camera and microphone of the victim's phone, or through the victim's social media account. In this work, we propose the Real Time Captcha (rtCaptcha) system, which stops/slows down such an attack by turning the adversary's task from creating authentic video/audio of the target victim performing known authentication tasks (e.g., smile, blink) to figuring out what is the authentication task, which is encoded as a Captcha. Specifically, when a user tries to authenticate using rtCaptcha, they will be presented a Captcha and will be asked to take a "selfie" video while announcing the answer to the Captcha. As such, the security guarantee of our system comes from the strength of Captcha, and not how well we can distinguish real faces/voices from synthesized ones. To demonstrate the usability and security of rtCaptcha, we conducted a user study to measure human response times to the most popular Captcha schemes. Our experiments show that, thanks to the humans' speed of solving Captchas, adversaries will have to solve Captchas in less than 2 seconds in order to appear live/human and defeat rtCaptcha, which is not possible for the best settings on the attack side.

show abstract

Section: B Compromising Attacks and Defensesmentioning

confidence: 99%

Section: Facial Authentication Systems Studiedmentioning

confidence: 99%

rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System

Uzun¹

2018

Proceedings 2018 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

show abstract

“…2 Secondly, Bolkart, Brunton, Salazar and Wuhrer have a website where they provide 3DMMs constructed by their recent works, modelling 3D face shapes of different subjects in neutral expression (Brunton et al 2014b) as well as 3D shapes of different subjects in different expressions (Brunton et al 2014a, Bolkart and. 3 Finally, a University of Surrey website provides a range of 3D facial shape models of varying resolutions (Huber et al 2016). 4…”

Section: Previous Workmentioning

confidence: 99%

“…We compare with three publicly available Morphable Models of human faces in neutral expression, namely the BFM model (Paysan et al 2009a, Paysan et al 2009b), the PCA model of Brunton et al (2014b), Bolkart et al (2013), which will be hereafter referred to as Brunton et al model, and the Surrey face model (Huber et al 2016). Note that for the sake of fairness towards the existing models, we do not consider the bespoke LSFM models in the fitting experiment, since these models use additional information related to demographics.…”

Section: Fitting Applicationmentioning

confidence: 99%

Large Scale 3D Morphable Models

et al. 2017

View full text Add to dashboard Cite

We present large scale facial model (LSFM)-a 3D Morphable Model (3DMM) automatically constructed from 9663 distinct facial identities. To the best of our knowledge LSFM is the largest-scale Morphable Model ever constructed, containing statistical information from a huge variety of the human population. To build such a large model we introduce a novel fully automated and robust Morphable Model construction pipeline, informed by an evaluation of state-of-the-art dense correspondence techniques. The dataset that LSFM is trained on includes rich demographic information about each subject, allowing for the construction of not only a global 3DMM model but also models tailored for specific age, gender or ethnicity groups. We utilize the proposed model to perform age classification from 3D shape alone and to reconstruct noisy out-of-sample data in the low-dimensional model space. Furthermore, we perform a systematic analysis of the constructed 3DMM models that showcases their quality and descriptive power. reveal that the proposed 3DMM achieves state-of-the-art results, outperforming existing models by a large margin. Finally, for the benefit of the research community, we make publicly available the source code of the proposed automatic 3DMM construction pipeline, as well as the constructed global 3DMM and a variety of bespoke models tailored by age, gender and ethnicity.

show abstract

“…the FRGC dataset [43], the Bosphorus 3D face dataset [50], the FaceWarehouse dataset [5], the Basel Face Model (BFM) [42] and the Surrey 3D face model [28]. However, both the Surrey and Basel face models were constructed using small datasets that lack diverse ethnicities.…”

mentioning

confidence: 99%

Gaussian mixture 3D morphable face model

Koppen

Feng

Kittler

et al. 2018

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

Abstract3D Morphable Face Models (3DMM) have been used in pattern recognition for some time now. They have been applied as a basis for 3D face recognition, as well as in an assistive role for 2D face recognition to perform geometric and photometric normalisation of the input image, or in 2D face recognition system training. The statistical distribution underlying 3DMM is Gaussian. However, the single-Gaussian model seems at odds with reality when we consider different cohorts of data, e.g. Black and Chinese faces. Their means are clearly different. This paper introduces the Gaussian Mixture 3DMM (GM-3DMM) which models the global population as a mixture of Gaussian subpopulations, each with its own mean. The proposed GM-3DMM extends the traditional 3DMM naturally, by adopting a shared covariance structure to mitigate small sample estimation problems associated with data in high dimensional spaces. We construct a GM-3DMM, the training of which involves a multiple cohort dataset, SURREY-JNU, comprising 942 3D face scans of people with mixed backgrounds. Experiments in fitting the GM-3DMM to 2D face images to facilitate their geometric and photometric normalisation for pose and illumination invariant face recognition demonstrate the merits of the proposed mixture of Gaussians 3D face model.

show abstract

A Multiresolution 3D Morphable Face Model and Fitting Framework

Cited by 209 publications

References 15 publications

rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System

rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System

Large Scale 3D Morphable Models

Gaussian mixture 3D morphable face model

Contact Info

Product

Resources

About