Learning from Millions of 3D Scans for Large-Scale 3D Face Recognition

Gilani, Syed Zulqarnain; Mian, Ajmal

doi:10.1109/cvpr.2018.00203

Cited by 76 publications

(62 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rank-1 Recognition Accuracy MMH (2D + 3D) [5] 94.20% K3DM (3D) [4] 96.00% FR3DNet F T (3D) [6] 98.00% Proposed (3D) 99.98% Table 2. Comparison of 3DS with state-of-art methods on the dynamic BU4DFE dataset.…”

Section: D Fr Methodsmentioning

confidence: 99%

“…It has been also recently addressed by means of deep Thanks to the National Research Fund (FNR), Luxembourg, for funding this work under the agreement C-PPP17/IS/11643091/IDform/Aouada. learning [6]. There are many surveys in literature reporting progress on FR [7,8].…”

Section: Introductionmentioning

confidence: 99%

“…FR is then based on matching the model features between different instances. This work is compared to the works of [5,4,6] in Section 4 which are briefly described here.…”

Section: Introductionmentioning

confidence: 99%

“…In order to mitigate the deformations effect, they had to remove these points in the fitting process. The work of [6] proposed a deep architecture to learn 3D facial features. Each 3D Point Cloud (PC) was used to generate an image with 3-channels from three different fitting operations.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

3d Deformation Signature for Dynamic Face Recognition

Shabayek

Aouada

Cherenkova

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This work proposes a novel 3D Deformation Signature (3DS) to represent a 3D deformation signal for 3D Dynamic Face Recognition. 3DS is computed given a non-linear 6D-space representation which guarantees physically plausible 3D deformations. A unique deformation indicator is computed per triangle in a triangulated mesh as a ratio derived from scale and in-plane deformation in the canonical space. These indicators, concatenated, construct the 3DS for each temporal instance. There is a pressing need of non-intrusive bio-metric measurements in domains like surveillance and security. By construction, 3DS is a non-intrusive facial measurement that is resistant to common security attacks like presentation, template and adversarial attacks. Two dynamic datasets (BU4DFE and COMA) were examined, in a standard classification framework, to evaluate 3DS. A first rank recognition accuracy of 99.9%, that outperforms existing literature, was achieved. Assuming an open-world setting, 99.97% accuracy was attained in detecting unseen distractors.

show abstract

Section: D Fr Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…FR is then based on matching the model features between different instances. This work is compared to the works of [5,4,6] in Section 4 which are briefly described here.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

3d Deformation Signature for Dynamic Face Recognition

Shabayek

Aouada

Cherenkova

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…High-quality 3D face reconstruction is an important problem in computer vision and graphics [38] that is related to various applications such as digital actor [3], face recognition [5,48] and animation [3,21,40]. Some works have been devoted to solving this problem at the source, using either multi-view information [15,43] or the illumination conditions [1,2,37].…”

Section: Introductionmentioning

confidence: 99%

Lightweight Photometric Stereo for Facial Details Recovery

Guo

Deng

Zhang

2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Recently, 3D face reconstruction from a single image has achieved great success with the help of deep learning and shape prior knowledge, but they often fail to produce accurate geometry details. On the other hand, photometric stereo methods can recover reliable geometry details, but require dense inputs and need to solve a complex optimization problem. In this paper, we present a lightweight strategy that only requires sparse inputs or even a single image to recover high-fidelity face shapes with images captured under near-field lights. To this end, we construct a dataset containing 84 different subjects with 29 expressions under 3 different lights. Data augmentation is applied to enrich the data in terms of diversity in identity, lighting, expression, etc. With this constructed dataset, we propose a novel neural network specially designed for photometric stereo based 3D face reconstruction. Extensive experiments and comparisons demonstrate that our method can generate high-quality reconstruction results with one to three facial images captured under near-field lights. Our full framework is available at https://github.com/Juyong/FacePSNet.

show abstract

References

2018

3D Shape Analysis

View full text Add to dashboard Cite

Learning from Millions of 3D Scans for Large-Scale 3D Face Recognition

Cited by 76 publications

References 46 publications

3d Deformation Signature for Dynamic Face Recognition

3d Deformation Signature for Dynamic Face Recognition

Lightweight Photometric Stereo for Facial Details Recovery

References

Contact Info

Product

Resources

About