3D Face Reconstruction from 2D Images

Widanagamaachchi, Wathsala; Dharmaratne, Anuja

doi:10.1109/dicta.2008.83

Cited by 24 publications

(13 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Manipulating and replacing facial expressions in photographs and videos has gained more attention in recent years [19]. Previous approaches fall into four categories: 3D-based, 2D expression mapping based, flow-based and image reordering based approaches.…”

Section: Related Workmentioning

confidence: 99%

Facial expression editing in video using a temporally-smooth factorization

Yang

Bourdev

Shechtman

et al. 2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

We address the problem of editing facial expression in video, such as exaggerating, attenuating or replacing the expression with a different one in some parts of the video. To achieve this we develop a tensor-based 3D face geometry reconstruction method, which fits a 3D model for each video frame, with the constraint that all models have the same identity and requiring temporal continuity of pose and expression. With the identity constraint, the differences between the underlying 3D shapes capture only changes in expression and pose. We show that various expression editing tasks in video can be achieved by combining face reordering with face warping, where the warp is induced by projecting differences in 3D face shapes into the image plane. Analogously, we show how the identity can be manipulated while fixing expression and pose. Experimental results show that our method can effectively edit expressions and identity in video in a temporally-coherent way with high fidelity.

show abstract

Section: Related Workmentioning

confidence: 99%

Facial expression editing in video using a temporally-smooth factorization

Yang

Bourdev

Shechtman

et al. 2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Human head is difficult to model even using normal 3D modeling software [4] hence the reconstruction of human face is being studied in last few decades [5] [9]. The humans can perceive the 3D shape of a 2D image by just looking at it, even if the object in the image is completely new to the eye.…”

Section: Introductionmentioning

confidence: 99%

“…The humans can perceive the 3D shape of a 2D image by just looking at it, even if the object in the image is completely new to the eye. The human eye signals the brain about the object through a nerve signal and from this nerve signal, the brain creates the 3D shape of the 2D object [4]. The same process is used for 3D generation in real life.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reconstruct 3d Human Face Using Two Orthogonal Images

Mazumdar¹

2014

IJRET

View full text Add to dashboard Cite

show abstract

“…The generic face model has been used in various applications since it has a uniform point distribution and provides a detailed face shape with a small number of points (3,4,5,6). Among the previous approaches, radial basis function (RBF) is used in this paper.…”

Section: Generic Model Fittingmentioning

confidence: 99%

3D Face Modeling using Face Image

Kim¹,

Ban²,

Park³

et al. 2015

Journal of International Society for Simulation Surgery

View full text Add to dashboard Cite

IntroductionThe big popularity of plastic surgery has created a booming plastic surgery industry. Due to the prevalence of plastic surgery, the importance of plastic surgery patients' satisfaction has been increasing. It has thus never been more important for plastic surgeons to rigorously measure and report on patient satisfaction and quality of life following aesthetic procedures. According to the study, among the patients who have had plastic surgery, nearly 20% of surgery patients reported their normal appearance altered in an unfavorable way. To remedy such problem, our study focuses on 3D face modeling. 3D face modeling can realistically express face deformation and pose variation with depth information. This method can generate highly accurate 3D facial shapes by using real 3D information calculated from the camera geometry. With these advantages, 3D face models can be applied to estimate plastic surgery result for patients. By calculating patients' 3D facial shapes after the surgery, it can be expected the rate of a failure of plastic surgery can decrease significantly (1, 2).In this paper, we aim to develop a realistic 3D face modeling method that generates accurate 3D face modeling for plastic surgery results. First, we get 3D FSMs which are calculated from pre-defined feature points. Second, to get a detailed face shape, generic model fitting is performed. Finally, texture mapping is applied by stitching face parts. Thus, we can provide a 3D deformable face modeling to be used to preview the surgery result and be provided to plastic surgery patients. Materials and MethodsTo introduce the proposed system, Fig. 1 shows a workflow of the whole process in this paper. 3D Face Shape Estimation using Multi-view 3D FSMs in the Mirror SystemA method proposed uses two mirrors on each side of the front face to overcome the lack of depth direction. Since synchronization problem may arise when using cameras, the mirror system was employed instead of adding the cameras.A proposed method uses the pre-defined feature points. These points are used to calculate 3D coordinates by adjusting param- PurposeZZIt has been stated that patient satisfaction is the crucial factor for determining success in plastic surgery. The convergence of medical science and computer vision has made easier to satisfy patients who wants to have plastic surgery. In this paper, we try to apply 3D face modeling in plastic surgical area.Materials and MethodsZZThe author introduces a method for accurate 3D face modeling techniques using a statistical model-based 3D face modeling approach in a mirror system.ResultsZZWe could successfully obtain highly accurate 3D face shape results.ConclusionZZThe method suggested could be used for acquiring 3D face models from 2D face image and the result obtained from this could be effectively used for plastic surgical areas. Generic Model FittingAfter 3D face shape estimation, the 3D positions of other vertices can be determined by a generic 3D face model. The generic face model has been used in various applica...

show abstract

3D Face Reconstruction from 2D Images

Cited by 24 publications

References 6 publications

Facial expression editing in video using a temporally-smooth factorization

Facial expression editing in video using a temporally-smooth factorization

Reconstruct 3d Human Face Using Two Orthogonal Images

3D Face Modeling using Face Image

Contact Info

Product

Resources

About