3D face modeling based on structure optimization and surface reconstruction with B-Spline

Peng, Weilong; Xu, Chao; Feng, Zhiyong

doi:10.1016/j.neucom.2015.11.090

Cited by 13 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been works of fitting B-splines to noisy 3D data, like Hoch et al (1998). B-spline face model is a continuous free-form surface that can be reconstructed from images directly, instead of intermediate point data, but it is not a detailed model by only using structure optimization (Peng et al, 2016). Because B-spline surface is a special case of NURBS (Non-Uniform Rational B-Spline) (Piegl and Tiller, 1997), it can also be imported to 3D modeling software like Rhino3D for further editing, analysis, and transformation conveniently by adjusting the B-spline control points.…”

Section: Facial Surface Modelingmentioning

confidence: 99%

Geometrical Consistency Modeling on B-Spline Parameter Domain for 3D Face Reconstruction From Limited Number of Wild Images

Peng

Tang³

et al. 2021

Front. Neurorobot.

Self Cite

View full text Add to dashboard Cite

A number of methods have been proposed for face reconstruction from single/multiple image(s). However, it is still a challenge to do reconstruction for limited number of wild images, in which there exists complex different imaging conditions, various face appearance, and limited number of high-quality images. And most current mesh model based methods cannot generate high-quality face model because of the local mapping deviation in geometric optics and distortion error brought by discrete differential operation. In this paper, accurate geometrical consistency modeling on B-spline parameter domain is proposed to reconstruct high-quality face surface from the various images. The modeling is completely consistent with the law of geometric optics, and B-spline reduces the distortion during surface deformation. In our method, 0th- and 1st-order consistency of stereo are formulated based on low-rank texture structures and local normals, respectively, to approach the pinpoint geometric modeling for face reconstruction. A practical solution combining the two consistency as well as an iterative algorithm is proposed to optimize high-detailed B-spline face effectively. Extensive empirical evaluations on synthetic data and unconstrained data are conducted, and the experimental results demonstrate the effectiveness of our method on challenging scenario, e.g., limited number of images with different head poses, illuminations, and expressions.

show abstract

Section: Facial Surface Modelingmentioning

confidence: 99%

Geometrical Consistency Modeling on B-Spline Parameter Domain for 3D Face Reconstruction From Limited Number of Wild Images

Peng

Tang³

et al. 2021

Front. Neurorobot.

Self Cite

View full text Add to dashboard Cite

show abstract

“…A performance comparison between the proposed method and some existing methods, both qualitatively and quantitatively, is conducted. For qualitative analysis, [36] and [37] are compared with our method, whereas quantitative analysis is performed by comparing our method with [38] and [39]. For qualitative comparison, internet celebrity pictures (George Clooney, Kevin Spacey, and Tom Hanks) are used, whereas quantitative comparison is performed on the images used in these papers (face I, face II and bs000).…”

Section: Evaluationsmentioning

confidence: 99%

“…The qualitative comparison between our method and other methods has demonstrated the superiority of our method. To consider the objective aspects, we have also compared our method quantitatively with more methods explained in [38] and [39]. For quantitative measurements, the following factors are calculated: root mean square error (RMSE), mean error, standard deviation (Std.)…”

Section: Evaluationsmentioning

confidence: 99%

3D Face Reconstruction From Single 2D Image Using Distinctive Features

et al. 2020

View full text Add to dashboard Cite

3D face reconstruction is considered to be a useful computer vision tool, though it is difficult to build. This paper proposes a 3D face reconstruction method, which is easy to implement and computationally efficient. It takes a single 2D image as input, and gives 3D reconstructed images as output. Our method primarily consists of three main steps: feature extraction, depth calculation, and creation of a 3D image from the processed image using a Basel face model (BFM). First, the features of a single 2D image are extracted using a two-step process. Before distinctive-features extraction, a face must be detected to confirm whether one is present in the input image or not. For this purpose, facial features like eyes, nose, and mouth are extracted. Then, distinctive features are mined by using scale-invariant feature transform (SIFT), which will be used for 3D face reconstruction at a later stage. Second step comprises of depth calculation, to assign the image a third dimension. Multivariate Gaussian distribution helps to find the third dimension, which is further tuned using shading cues that are obtained by the shape from shading (SFS) technique. Thirdly, the data obtained from the above two steps will be used to create a 3D image using BFM. The proposed method does not rely on multiple images, lightening the computation burden. Experiments were carried out on different 2D images to validate the proposed method and compared its performance to those of the latest approaches. Experiment results demonstrate that the proposed method is time efficient and robust in nature, and it outperformed all of the tested methods in terms of detail recovery and accuracy.

show abstract

“…Any triangulation procedure has to be able to allow control over the analyzed surface topology and any other after modifications: dividing the surface along an incorporated curve in order to define a new edge or sticking two surfaces together in order to form a mutual boundary edge [8].…”

Section: Topology Changementioning

confidence: 99%

“…But this tedious work will only harden even more the process by accumulating an even larger number of operations in the case of free form surfaces [8].…”

Section: Control Tools For Outer Shapesmentioning

confidence: 99%

Aspects to be considered in case of variable surfaces modelling

2017

View full text Add to dashboard Cite

Abstract. Proper triangulation will bring benefits regarding the numerical conditioning of nodes within the point cloud but will also allow certain nodes to be able to move around those that are neighboring them. In this way, surface features as chained regions or curves will have a certain degree of freedom which will allow them to slide one towards another. At a more careful evaluation there is a major drawback in terms of lack of possibility to take into consideration the operations which depend upon approximate shapes inside the ideal shape evaluation process. In order to be able to control the accuracy of the process there is an impetuous need for all surfaces to be described functionally. Any triangulation procedure has to be able to allow control over the analyzed surface topology and any other after modifications: dividing the surface along an incorporated curve in order to define a new edge or sticking two surfaces together in order to form a mutual boundary edge.

show abstract

3D face modeling based on structure optimization and surface reconstruction with B-Spline

Cited by 13 publications

References 31 publications

Geometrical Consistency Modeling on B-Spline Parameter Domain for 3D Face Reconstruction From Limited Number of Wild Images

Geometrical Consistency Modeling on B-Spline Parameter Domain for 3D Face Reconstruction From Limited Number of Wild Images

3D Face Reconstruction From Single 2D Image Using Distinctive Features

Aspects to be considered in case of variable surfaces modelling

Contact Info

Product

Resources

About