TR2006-072

A Statistical Model for Synthesis of Detailed Facial Geometry


    •  Golovinskiy, A., Matusik, W., Pfister, H., Rusinkiewicz, S., Funkhouser, T., "A Statistical Model for Synthesis of Detailed Facial Geometry", ACM Transactions on Graphics (TOG), Vol. 25, No. 3, pp. 1025-1034, July 2006.
      BibTeX TR2006-072 PDF
      • @article{Golovinskiy2006jul,
      • author = {Golovinskiy, A. and Matusik, W. and Pfister, H. and Rusinkiewicz, S. and Funkhouser, T.},
      • title = {A Statistical Model for Synthesis of Detailed Facial Geometry},
      • journal = {ACM Transactions on Graphics (TOG)},
      • year = 2006,
      • volume = 25,
      • number = 3,
      • pages = {1025--1034},
      • month = jul,
      • issn = {0730-0301},
      • url = {https://www.merl.com/publications/TR2006-072}
      • }
  • Research Area:

    Computer Vision

Abstract:

Detailed surface geometry contributes greatly to the visual realism of 3D face models. However, acquiring high-resolution face geometry is often tedious and expensive. Consequently, most face models used in games, virtual reality or computer vision look unrealistically smooth. In this paper, we introduce a new statistical technique for the analysis and synthesis of small three-dimensional facial features, such as wrinkles and pores. We acquire high-resolution face geometry for people across a wide range of ages, genders and races. For each scan, we separate the skin surface details from a smooth base mesh using displaced subdivision surfaces. Then, we analyze the resulting displacement maps using the texture analysis/synthesis framework of Heeger and Bergen, adapted to capture statistics that vary spatially across a face. Finally, we use the extracted statistics to synthesize plausible detail on face meshes of arbitrary subjects. We demonstrate the effectiveness of this method in several applications, including analysis of facial texture in subjects with different ages and genders, interpolation between high-resolution face scans, adding detail to low-resolution face scans, and adjusting the apparent age of faces. In all cases, we are able to re-produce fine geometric details consistent with those observed in high resolution scans.

 

  • Related News & Events

    •  NEWS    ACM Transactions on Graphics (TOG): 7 publications by Amit Agrawal, Ramesh Raskar and others
      Date: July 15, 2006
      Where: ACM Transactions on Graphics (TOG)
      Research Area: Computer Vision
      Brief
      • The articles "Coded Exposure Photography: Motion Deblurring Using Fluttered Shutter" by Raskar, R., Agrawal, A. and Tumblin, J., "Fast Separation of Direct and Global Components of a Scene Using High Frequency Illumination" by Nayar, S.K., Krishnan, G., Grossberg, M.D. and Raskar, R., "Analysis of Human Faces using a measurement-Based Skin Reflectance Model" by Weyrich, T., Matusik, W., Pfister, H., Bickel, B., Donner, C., Tu, C., McAndless, J., Lee, J., Ngan, A., Jensen, H. and Gross, M., "Inverse Shade Trees for Non-Parametric Material Representation and Editing" by Lawrence, J., Ben-Artzi, A., DeCoro, C., Matusik, W., Pfister, H., Ramamoorthi, R. and Rusinkiewicz, S., "A Compact Factored Representation of Heterogeneous Subsurface Scattering" by Peers, P., Berge, K., Matusik, W., Ramamoorthi, R., Lawrence, J., Rusinkiewicz, S. and Dutre, P., "Time-Varying Surface Appearance: Acquisition, Modeling and Rendering" by Gu, J., Tu, C., Ramamoorthi, R., Belhumeur, P., Matusik, W. and Nayar, S. and "A Statistical Model for Synthesis of Detailed Facial Geometry" by Golovinskiy, A., Matusik, W., Pfister, H., Rusinkiewicz, S. and Funkhouser, T. were published in ACM Transactions on Graphics (TOG).
    •