방송공학회논문지 (Journal of Broadcast Engineering)

  • 제13권3호
  • /
  • Pages.339-349
  • /
  • 2008
  • /
  • 1226-7953(pISSN)
  • /
  • 2287-9137(eISSN)
한국방송∙미디어공학회 (The Korean Institute of Broadcast and Media Engineers)
권호 표지
DOI QR코드

DOI QR Code

가상 복사조도 반구와 반사계수에 근거한 얼굴 재조명

Face Relighting Based on Virtual Irradiance Sphere and Reflection Coefficients

  • 한희철 (연세대학교 전기전자공학과) ;
  • 손광훈 (연세대학교 전기전자공학과)
  • Han, Hee-Chul (School of Electrical and Electronic Engineering, Yonsei University) ;
  • Sohn, Kwang-Hoon (School of Electrical and Electronic Engineering, Yonsei University)
  • 발행 : 2008.05.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 임의의 알려지지 않은 조명 상황 하에서 3차원 객체의 텍스처 영상 한 장을 이용하여 광원의 위치를 추정하고 이를 이용해 조명에 의해 왜곡되어 있는 얼굴 영상을 재조명하는 기법을 제안한다. 우선 주어진 텍스처 영상으로부터 광원의 위치를 추정하기 위해 법선 벡터와 가중 양선형 보간을 이용하여 가상 복사조도 반구를 만들었다. 이를 이용해 추정된 주변광과 확산광 계수로 재조명 방정식을 도출하였다. 얼굴 텍스처 영상에서의 그림자와 음영을 원색으로 복원하는 알고리즘의 효율성과 정확성을 보이기 위해 광원의 위치 추정, 재조명, 얼굴 인식 등의 다양한 실험 결과를 보였다. 실험결과에 의하여 제안한 알고리즘은 조명에 강인한 얼굴 인식시스템뿐만 아니라 3차원 디스플레이에서의 작업 시 시각적 피로감을 줄이고 작업 효율을 높일 수 있음을 확인하였다.

We present a novel method to estimate the light source direction and relight a face texture image of a single 3D model under arbitrary unknown illumination conditions. We create a virtual irradiance sphere to detect the light source direction from a given illuminated texture image using both normal vector mapping and weighted bilinear interpolation. We then induce a relighting equation with estimated ambient and diffuse coefficients. We provide the result of a series of experiments on light source estimation, relighting and face recognition to show the efficiency and accuracy of the proposed method in restoring the shading and shadows areas of a face texture image. Our approach for face relighting can be used for not only illuminant invariant face recognition applications but also reducing visual load and Improving visual performance in tasks using 3D displays.

키워드

참고문헌

  1. A.S. Georghiades, P.N. Belhumeur, & D.J Kriegman, "From few to many: illumination cone models for face recognition under differing pose and lighting", IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(6), pp.643-660, 2001 https://doi.org/10.1109/34.927464
  2. R. Basria & D. Jacobs, "Lambertian reflectance and linear subspaces", Proc. 8th IEEE Int. Com. on Computer Vision, pp.383-390, 2001 https://doi.org/10.1109/ICCV.2001.937651
  3. L.. Zhang, S. Wang, & D. Samaras, "Face synthesis and recognition under arbitrary unknown lighting using a spherical harmonic basis morphable model", IEEE Conf on Computer Vision and Pattern Recognition, II: pp.209-216, 2005 https://doi.org/10.1109/CVPR.2005.152
  4. G. Gordon, "Face recognition based on depth maps and surface curvature", SPIE Geom. Methods Computer Vision, 1570, pp.234-247, 1991
  5. Z. Wen, Z. Liu, & T. Huang, "Face relighting with radiance environment maps", Proc. of IEEE Conf on Computer Vision and Pattern Recognition, pp.158-165, 2003 https://doi.org/10.1109/CVPR.2003.1211466
  6. J. Lee, H. Pfister, & B. Moghaddam, and R. Machiraju, "Estimation of 3Dfaces and illumination from single photographs using a bilinear illumination model", Proc. of Eurographics Symposium on Rendering, pp.73-82, 2005
  7. Y. Zhang & Y.-H. Yang, "Illuminant direction detennination for multiple light sources", Proc. IEEE Conf. on Computer Vision and Pattern Recognition, I pp.269-276, 2000 https://doi.org/10.1109/CVPR.2000.855829
  8. Y. Wang & D. Samaras, "Estimation of multiple directional light sources for synthesis of mixed reality images", Proc. 10th Pacific Conf. on Computer Graphics and Applications, pp.38-47 ,2002 https://doi.org/10.1109/PCCGA.2002.1167837
  9. T. Okabe, I. Sato, & Y. Sato, "Spherical harmonics vs. Haar wavelets: basis for recovering illumination from cast shadows", Proc. IEEE Conf. on Computer Vision and Pattern Recognition, I, pp.50-57, 2004 https://doi.org/10.1109/CVPR.2004.1315013
  10. C.S. Bouganis & M. Brookes, "Multiple light source detection", IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(4), pp.509-514, 2004 https://doi.org/10.1109/TPAMI.2004.1265865
  11. Y. Zhang & Y.-H. Yang, "Multiple illuminant direction detection with application to image synthesis", IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(8), pp.915-920, 2001 https://doi.org/10.1109/34.946995
  12. K. Hara, K. Nishino, & K. Ikeuchi, "Multiple light sources and re- 349 flectance property estimation based on a mixture of spherical distributions", Proc. IntI. Conf. on Computer Vision, II: pp.1627-1634, 2005 https://doi.org/10.1109/ICCV.2005.162
  13. Nathan Funk, "Implementation ofan illuminant detection algorithm", Project report for CMPUT 615 in University of Alberta, 2003
  14. JL. Bentley, "Multidimensional binary search trees used for associative searching", Communications ofthe ACM, 19, pp.509-517, 1975
  15. S. Arya, D. Mount, N. Netanyahu, R Silvennan, A. Wu, "An optimal algorithm for approximate nearest neighbor searching in fixed dimensions", Journal ofthe ACM, 45:6, pp.891-923, 1998 https://doi.org/10.1145/293347.293348
  16. D. Mount, S. Arya, "ANN: A library for approximate nearest neighbor searching", http://www.cs.umd.edu/~mount/ANN, 2006
  17. Turk M, Pentland A, "Eigenfaces for recognition", Journal of Cognitive Neuroscience, 3, pp.71-86, 1991 https://doi.org/10.1162/jocn.1991.3.1.71
  18. Russ T, Boehnen C, Peters T, "3D Face Recognition Using 3D Alignment for PCA", CVPR, II, pp.1391-1398, 2006 https://doi.org/10.1109/CVPR.2006.13