Journal of IKEEE (전기전자학회논문지)

Institute of Korean Electrical and Electronics Engineers (한국전기전자학회)
권호 표지
DOI QR코드

DOI QR Code

A Deep Learning-Based Face Mesh Data Denoising System

딥 러닝 기반 얼굴 메쉬 데이터 디노이징 시스템

  • Roh, Jihyun (Dept. of Computer Science, Kangwon National University) ;
  • Im, Hyeonseung (Dept. of Computer Science, Kangwon National University) ;
  • Kim, Jongmin (Dept. of Computer Science, Kangwon National University)
  • Received : 2019.12.06
  • Accepted : 2019.12.26
  • Published : 2019.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Although one can easily generate real-world 3D mesh data using a 3D printer or a depth camera, the generated data inevitably includes unnecessary noise. Therefore, mesh denoising is essential to obtain intact 3D mesh data. However, conventional mathematical denoising methods require preprocessing and often eliminate some important features of the 3D mesh. To address this problem, this paper proposes a deep learning based 3D mesh denoising method. Specifically, we propose a convolution-based autoencoder model consisting of an encoder and a decoder. The convolution operation applied to the mesh data performs denoising considering the relationship between each vertex constituting the mesh data and the surrounding vertices. When the convolution is completed, a sampling operation is performed to improve the learning speed. Experimental results show that the proposed autoencoder model produces faster and higher quality denoised data than the conventional methods.

3차원 프린터나 깊이 카메라 등을 이용하면 실세계의 3차원 메쉬 데이터를 손쉽게 생성할 수 있지만, 이렇게 생성된 데이터에는 필연적으로 불필요한 노이즈가 포함되어 있다. 따라서, 온전한 3차원 메쉬 데이터를 얻기 위해서는 메쉬 디노이징 작업이 필수적이다. 하지만 기존의 수학적인 디노이징 방법들은 전처리 작업이 필요하며 3차원 메쉬의 일부 중요한 특징들이 사라지는 문제점이 있다. 본 논문에서는 이러한 문제를 해결하기 위해 딥 러닝 기반의 3차원 메쉬 디노이징 기법을 소개한다. 구체적으로 본 논문에서는 인코더와 디코더로 구성된 컨볼루션 기반 오토인코더 모델을 제안한다. 메쉬 데이터에 적용하는 컨볼루션 연산은 메쉬 데이터를 구성하고 있는 각각의 정점과 그 주변의 정점들 간의 관계를 고려하여 디노이징을 수행하며, 컨볼루션이 완료되면 학습 속도 향상을 위해 샘플링 연산을 수행한다. 실험 결과, 본 논문에서 제안한 오토인코더 모델이 기존 방식보다 더 빠르고 더 높은 품질의 디노이징된 데이터를 생성함을 확인하였다.

Keywords

References

  1. G. Taubin, "A signal processing approach to fair surface design," In SIGGRAPH, pp.351-358, 1995. DOI: 10.1145/218380.218473
  2. M. Desbrun, M. Meyer, P. Schrooder, and A. H. Barr, "Implicit fairing of irregular meshes using diffusion and curvature flow," In SIGGRAPH, pp.317-324, 1999. DOI: 10.1145/311535.311576
  3. A. Nealen, T. Igarashi, O. Sorkine, and M. Alexa, "Laplacian mesh optimization," In Proceedings of the 4th international conference on Computer graphics and interactive techniques in Australasia and Southeast Asia (GRAPHITE '06), pp.381-389, 2006. DOI: 10.1145/1174429.1174494
  4. U. Clarenz, U. Diewald, and M. Rumpf, "Anisotropic geometric diffusion in surface processing," In Proc. of the conference on Visualization, pp.397-405, 2000. DOI: 10.1109/VISUAL.2000.885721
  5. T. Tasdizen, R. Whitaker, P. Burchard, and S. Osher, "Geometric surface smoothing via anisotropic diffusion of normals," In Proc. of the conference on Visualization, pp.125-132 2002. DOI: 10.1109/VISUAL.2002.1183766
  6. C. L. Bajaj and G. Xu, "Anisotropic diffusion of surfaces and functions on surfaces," ACM Trans. Graph., Vol.22, No.1, pp.4-32, 2003. DOI: 10.1145/588272.588276
  7. H. Yagou, Y. Ohtake, and A. Belyaev, "Mesh denoising via iterative alpha-trimming and nonlinear diffusion of normals with automatic thresholding," In Computer Graphics International, pp.28-33, 2003. DOI: 10.1109/CGI.2003.1214444
  8. K. Hildebrandt and K. Polthier, "Anisotropic filtering of non-linear surface features," Comput. Graph. Forum (EG), Vol.23, No.3, pp.391-400, 2004. DOI: 10.1111/j.1467-8659.2004.00770.x
  9. T. R. Jones, F. Durand, and M. Desbrun, "Noniterative, feature-preserving mesh smoothing," ACM Trans. Graph. (SIGGRAPH), Vol.22, No.3, pp.943-949, 2003. DOI: 10.1145/882262.882367
  10. S. Fleishman, I. Drori, and D. Cohen-Or, "Bilateral mesh denoising," ACM Trans. Graph. (SIGGRAPH), Vol.22, No.3, pp.950-953, 2003. DOI: 0.1145/882262.882368 https://doi.org/10.1145/882262.882368
  11. H. Yagou, Y. Ohtake, and A. Belyaev, "Mesh smoothing via mean and median filtering applied to face normals," In Geom. Model. and Proc., pp. 124-131, 2002. DOI: 10.1109/GMAP.2002.1027503
  12. Y. Shen and K. Barner, "Fuzzy vector median-based surface smoothing," IEEE. T. Vis. Comput. Gr., 10, 3, pp.252-265, 2004. DOI: 10.1109/TVCG.2004.1272725
  13. H. Fan, Y. Yu, and Q. Peng, "Robust featurepreserving mesh denoising based on consistent subneighborhoods," IEEE. T. Vis. Comput. Gr., 16, 2, pp.312-324, 2010. DOI: 10.1109/TVCG.2009.70
  14. X. Lu, Z. Deng, and W. Chen, "A robust scheme for feature-preserving mesh denoising," IEEE. T. Vis. Comput. Gr., Vol.22, No.3, pp. 1181-1194, 2016. DOI: 10.1109/TVCG.2015.2500222
  15. M. Wei, J. Yu, W.-M. Pang, J. Wang, J. Qin, L. Liu, P.-A. Heng, "Bi-normal filtering for mesh denoising," IEEE. T. Vis. Comput. Gr., Vol.21, No.1, pp.43-55, 2015. DOI: 10.1109/TVCG.2014.2326872
  16. A. Ranjan, T. Bolkart, S. Sanyal, M. J. Black, "Generating 3D Faces Using Convolutional Mesh Autoencoders," In ECCV 2018, pp.725-741, 2018.