Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network

Feng, Yong; Wu, Fan; Shao, Xin; Wang, Yanfeng; Zhou, Xi

doi:10.1007/978-3-030-01264-9_33

Cited by 649 publications

(631 citation statements)

References 73 publications

Supporting

Mentioning

583

Contrasting

Unclassified

Order By: Relevance

“…If a feature point is invisible, the feature block about the invisible point is not used as input, which is difficult to achieve for common 2D face alignment methods. Paper [16] designed a UV position map to represent 3D shape features of a complete human face in a 2D. The purpose of 3D face alignment is to reconstruct the 3D face from a 2D image, and then align the 3D face to the 2D image, so that 2D/3D face feature points can be located.…”

Section: D Face Alignmentmentioning

confidence: 99%

Dual Attention MobDenseNet(DAMDNet) for Robust 3D Face Alignment

Jiang

Kittler³

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

3D face alignment of monocular images is a crucial process in the recognition of faces with disguise.3D face reconstruction facilitated by alignment can restore the face structure which is helpful in detcting disguise interference.This paper proposes a dual attention mechanism and an efficient end-to-end 3D face alignment framework.We build a stable network model through Depthwise Separable Convolution, Densely Connected Convolutional and Lightweight Channel Attention Mechanism. In order to enhance the ability of the network model to extract the spatial features of the face region, we adopt Spatial Group-wise Feature enhancement module to improve the representation ability of the network. Different loss functions are applied jointly to constrain the 3D parameters of a 3D Morphable Model (3DMM) and its 3D vertices. We use a variety of data enhancement methods and generate large virtual pose face data sets to solve the data imbalance problem. The experiments on the challenging AFLW,AFLW2000-3D datasets show that our algorithm significantly improves the accuracy of 3D face alignment. Our experiments using the field DFW dataset show that DAMDNet exhibits excellent performance in the 3D alignment and reconstruction of challenging disguised faces.The model parameters and the complexity of the proposed method are also reduced significantly.The code is publicly available at https:// github.com/LeiJiangJNU/DAMDNet

show abstract

Section: D Face Alignmentmentioning

confidence: 99%

Dual Attention MobDenseNet(DAMDNet) for Robust 3D Face Alignment

Jiang

Kittler³

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

show abstract

“…One of the main challenges for learning 3D reconstruction models is the scarcity of 3D annotations. Strategies to overcome this issue range from using synthetic data [23,24,11] to fitting 3DMM to images [33,9]. However, the 3D ground truth produced by these strategies is subject to inaccuracies in the input data distribution caused by the renderers or in the target geometry caused by the fittings of the 3DMM.…”

Section: Datasetmentioning

confidence: 99%

Hyperparameter-Free Losses for Model-Based Monocular Reconstruction

Ramon¹,

Ruíz²,

Batard³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

This work proposes novel hyperparameter-free losses for single view 3D reconstruction with morphable models (3DMM). We dispense with the hyperparameters used in other works by exploiting geometry, so that the shape of the object and the camera pose are jointly optimized in a sole term expression. This simplification reduces the optimization time and its complexity. Moreover, we propose a novel implicit regularization technique based on random virtual projections that does not require additional 2D or 3D annotations. Our experiments suggest that minimizing a shape reprojection error together with the proposed implicit regularization is especially suitable for applications that require precise alignment between geometry and image spaces, such as augmented reality. We evaluate our losses on a large scale dataset with 3D ground truth and publish our implementations to facilitate reproducibility and public benchmarking in this field.

show abstract

“…Acquiring 3D scans is not scalable, but our experts wish to investigate the 3D structure of the faces. We offer to interpolate Buddha faces in a 3D model using joint reconstruction and dense alignment [6] (Fig. 1, d).…”

Section: Retrieval and Analysismentioning

confidence: 99%

BUDA.ART

Renoust

Franca

Chan

et al. 2019

Proceedings of the 27th ACM International Conference on Multimedia

View full text Add to dashboard Cite

We introduce BUDA.ART, a system designed to assist researchers in Art History, to explore and analyze an archive of pictures of Buddha statues. The system combines different CBIR and classical retrieval techniques to assemble 2D pictures, 3D statue scans and meta-data, that is focused on the Buddha facial characteristics. We build the system from an archive of 50,000 Buddhism pictures, identify unique Buddha statues, extract contextual information, and provide specific facial embedding to first index the archive. The system allows for mobile, on-site search, and to explore similarities of statues in the archive. In addition, we provide search visualization and 3D analysis of the statues.

show abstract

Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network

Cited by 649 publications

References 73 publications

Dual Attention MobDenseNet(DAMDNet) for Robust 3D Face Alignment

Dual Attention MobDenseNet(DAMDNet) for Robust 3D Face Alignment

Hyperparameter-Free Losses for Model-Based Monocular Reconstruction

BUDA.ART

Contact Info

Product

Resources

About