摘要
现有人脸纹理重建方法对于人脸的皱纹、胡须、瞳孔颜色等重建效果往往不够细致.为了解决此问题,文中提出基于人脸标准化的纹理和光照保持3D人脸重构.首先对2D人脸图像标准化,使用光照信息和对称纹理重构人脸自遮挡区域的纹理.然后依据2D-3D点对应关系从标准化的2D人脸图像获取相应的3D人脸纹理,结合人脸形状重构和纹理信息,得到最终的3D人脸重构结果.实验表明文中方法有效保留原始2D图像的纹理和光照信息,重构的人脸更自然,具有更丰富的人脸细节.
The results of the existing texture recovery methods are not detailed enough for the face features such as wrinkles, beards and pupil colors. Therefore, the texture and illumination preserving 3 D face reconstruction based on face normalization is proposed. Firstly, the 2 D facial image is normalized to reconstruct the self-occlusion area using illumination information and symmetric texture. Then, the corresponding 3 D face texture is obtained by the normalized 2 D image according to the 2 D-3 D point pairs. Finally, combining the face shape reconstruction and texture information, the final 3 D face reconstruction results are generated. The experimental results show that the proposed method preserves the texture and the illumination information of the original 2 D image effectively, and the reconstructed faces are more natural with more facial details.
引文
[1] BLANZ V,VETTER T.A Morphable Model for the Synthesis of 3D Faces // Proc of the 26th Annual Conference on Computer Graphics and Interactive Techniques.New York,USA:ACM,1999:187-194.
[2] 梁荣华,陈纯,张慧.一个三维人脸真实感模型重建算法.模式识别与人工智能,2003,16(1):116-121.(LIANG R H,CHEN C,ZHANG H.An Algorithm for 3D Realistic-Looking Facial Model Reconstruction.Pattern Recognition and Artificial Intelligence,2003,16(1):116-121.)
[3] CHU B,ROMDHANI S,CHEN L M.3D-Aided Face Recognition Robust to Expression and Pose Variations // Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2014:1907-1914.
[4] AMBERG B,KNOTHE R,VETTER T.Expression Invariant 3D Face Recognition with a Morphable Model // Proc of the 8th IEEE International Conference on Automatic Face and Gesture Recognition.Washington,USA:IEEE,2008.DOI:10.1109/AFGR.2008.4813376.
[5] CAO C,WENG Y L,ZHOU S,et al.Facewarehouse:A 3D Facial Expression Database for Visual Computing.IEEE Transactions on Visualization and Computer Graphics,2014,20(3):413-425.
[6] BLANZ V,MEHL A,VETTER T,et al.A Statistical Method for Robust 3D Surface Reconstruction from Sparse Data // Proc of the 2nd International Symposium on 3D Data Processing,Visualization and Transmission.Washington,USA:IEEE,2004:293-300.
[7] ROMDHANI S,VETTER T.Estimating 3D Shape and Texture Using Pixel Intensity,Edges,Specular Highlights,Texture Constraints and a Prior // Proc of the IEEE Computer Society Confe-rence on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2005,II:986-993.
[8] ZHU X Y,YAN J J,YI D,et al.Discriminative 3D Morphable Model Fitting // Proc of the 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition.Washington,USA:IEEE,2015.DOI:10.1109/FG.2015.7163096.
[9] LIU F,ZHAO Q J,LIU X M,et al.Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition[J/OL].[2019-01-13].http://cvlab.cse.msu.edu/pdfs/Liu_Zeng_Zhao_Liu_ECCV2016.pdf.
[10] HUBER P,FENG Z H,CHRISTMAS W,et al.Fitting 3D Morphable Face Models Using Local Features // Proc of the IEEE International Conference on Image Processing.Washington,USA:IEEE,2015:1195-1199.
[11] JOURABLOO A,LIU X M.Pose-Invariant 3D Face Alignment[C/OL].[2019-01-13].https://arxiv.org/pdf/1506.03799.pdf.
[12] ZHU X Y,LEI Z,LIU X M,et al.Face Alignment across Large Poses:A 3D Solution[C/OL].[2019-01-13].https://arxiv.org/pdf/1511.07212.pdf.
[13] DOU P F,SHAH S K,KAKADIARIS I A.End-to-End 3D Face Reconstruction with Deep Neural Networks[C/OL].[2019-01-13].https://arxiv.org/pdf/1704.05020.pdf.
[14] JOURABLOO A,LIU X M.Large-Pose Face Alignment via CNN-Based Dense 3D Model Fitting // Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2016:4188-4196.
[15] FENG Y,WU F,SHAO X H,et al.Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network[C/OL].[2019-01-13].https://arxiv.org/pdf/1803.07835.pdf.
[16] BLANZ V,SCHERBAUM K,VETTER T,et al.Exchanging Faces in Images.Computer Graphics Forum,2004,23(3):669-676.
[17] HU G S,YAN F,CHAN C H,et al.Face Recognition Using a Unified 3D Morphable Model // Proc of the European Conference on Computer Vision.Berlin,Germany:Springer,2016:73-89.
[18] MA M Y,HU X Y,XU Y Q,et al.A Lighting Robust Fitting Approach of 3D Morphable Model Using Spherical Harmonic Illumination // Proc of the 22nd International Conference on Pattern Recognition.Washington,USA:IEEE,2014:2101-2106.
[19] ZHU X Y,LEI Z,YAN J J,et al.High-Fidelity Pose and Expre-ssion Normalization for Face Recognition in the Wild // Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2015:787-796.
[20] PéREZ P,GANGNET M,BLAKE A.Poisson Image Editing.ACM Transactions on Graphics,2003,22(3):313-318.
[21] ZHANG L,SAMARAS D.Face Recognition from a Single Training Image under Arbitrary Unknown Lighting Using Spherical Harmonics.IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(3):351-363.
[22] ZHU X X,RAMANAN D.Face Detection,Pose Estimation,and Landmark Localization in the Wild // Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2012:2879-2886.
[23] BELHUMEUR P N,JACOBS D W,KRIEGMAN D J,et al.Localizing Parts of Faces Using a Consensus of Exemplars.IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(12):2930-2940.