Dual Neural Networks Coupling Data Regression With Explicit Priors for Monocular 3D Face Reconstruction

Fan, Xin; Cheng, Shuying; Huyan, Kang; Hou, Minjun; Liu, Risheng; Luo, Zhongxuan

doi:10.1109/tmm.2020.2994506

Cited by 23 publications

(9 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fan et al 18 proposed a data regression technique for face reconstruction that uses a pair of neural networks (DNNs). As an application of the suggested DNN technique, the convolution layer trains the data for the facial reconstruction process.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Framework for facial recognition and reconstruction for enhanced security and surveillance monitoring using 3D computer vision

Wang

Zhang

2023

J. Electron. Imag.

View full text Add to dashboard Cite

Workflows can be optimized with the use of three-dimensional (3D) computer vision (CV) by monitoring processes from many angles. The potential for increased efficiency and cost savings is clear here. Input scenarios are always being monitored by security and surveillance systems to recognize and classify items, human faces, and moving things. The input reconstruction in these surveillance systems is problematic because of the mapping from three dimensions to two dimensions in the form of pixels. We present a new 3D CV paradigm-based framework for facial recognition and reconstruction. In this setup, deep neural networks are used to distinguish between mapped and unmapped pixels during a 2D to 3D or 3D to 2D transformation. To use correlation analysis to recognize human faces, it is necessary to first examine the input image for textural properties. The mapping procedure continues with the extraction of textural elements using dimensional contours. Then, continuous contours are used to do the 3D mapping and reduce the number of false positives. Instead, this framework isolates individual contours of moving objects or faces to increase the number of training iterations. Finally, missing pixels in the dimension conversion are filled to rebuild the human face utilizing discrete and continuous outlines. Hence, the suggested framework minimizes the false rate (10%), increases the false positive rate as (13.93%), and minimizes the error by (9.89%) while maximizing the recognition accuracy for (13.93%) and the precision is (13.21%).

show abstract

Section: Related Workmentioning

confidence: 99%

“…Fan et al 18 . proposed a data regression technique for face reconstruction that uses a pair of neural networks (DNNs).…”

Section: Related Workmentioning

confidence: 99%

Framework for facial recognition and reconstruction for enhanced security and surveillance monitoring using 3D computer vision

Wang

Zhang

2023

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…To alleviate these limitations of the training set, many different training schemes and network architectures have been proposed, such as iterative training [7,52,53], generative adversarial networks [54,6,55], and training multiple networks each handling a specific task [56,51,57]. However, the approach that has been most exploited is the encoder-decoder architecture.…”

Section: Architecturementioning

confidence: 99%

BabyNet: Reconstructing 3D faces of babies from uncalibrated photographs

Morales¹,

Porras²,

Linguraru³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present a 3D face reconstruction system that aims at recovering the 3D facial geometry of babies from uncalibrated photographs, BabyNet. Since the 3D facial geometry of babies differs substantially from that of adults, baby-specific facial reconstruction systems are needed. BabyNet consists of two stages: 1) a 3D graph convolutional autoencoder learns a latent space of the baby 3D facial shape; and 2) a 2D encoder that maps photographs to the 3D latent space based on representative features extracted using transfer learning. In this way, using the pre-trained 3D decoder, we can recover a 3D face from 2D images. We evaluate BabyNet and show that 1) methods based on adult datasets cannot model the 3D facial geometry of babies, which proves the need for a babyspecific method, and 2) BabyNet outperforms classical model-fitting methods even when a baby-specific 3D morphable model, such as BabyFM, is used.

show abstract

“…Some other works directly obtained the full 3D geometry to avoid the restriction of parametric models and difficulty in pose estimation [47], [2], [45]. Jackson et al [21] proposed to use a volumetric representation of 3D face shape instead of the previously used point cloud or mesh and directly regressed the voxels.…”

Section: A 3d Face Reconstructionmentioning

confidence: 99%

SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction

Ruan

Zhang

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Three-dimensional face dense alignment and reconstruction in the wild is a challenging problem as partial facial information is commonly missing in occluded and large pose face images. Large head pose variations also increase the solution space and make the modeling more difficult. Our key idea is to model occlusion and pose to decompose this challenging task into several relatively more manageable subtasks. To this end, we propose an end-to-end framework, termed as Self-aligned Dual face Regression Network (SADRNet), which predicts a posedependent face, a pose-independent face. They are combined by an occlusion-aware self-alignment to generate the final 3D face. Extensive experiments on two popular benchmarks, AFLW2000-3D and Florence, demonstrate that the proposed method achieves significant superior performance over existing state-of-the-art methods.

show abstract

Dual Neural Networks Coupling Data Regression With Explicit Priors for Monocular 3D Face Reconstruction

Cited by 23 publications

References 43 publications

Framework for facial recognition and reconstruction for enhanced security and surveillance monitoring using 3D computer vision

Framework for facial recognition and reconstruction for enhanced security and surveillance monitoring using 3D computer vision

BabyNet: Reconstructing 3D faces of babies from uncalibrated photographs

SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction

Contact Info

Product

Resources

About