Abstract
We present a new method for reconstructing depth of a known object from a single still image using deformed underneath sign matrix of a similar object. Existing Shape from Shading(SFS) methods try to establish a relationship between intensity values of a still image and surface normal of corresponding depth, but most of them resort to error minimization based approaches. Given the fact that these reconstruction approaches are fundamentally ill-posed, they have limited successes for surfaces like a human face. Photometric Stereo (PS) or Structure from Motion (SfM) based methods extend SFS by adding additional information/constraints about the target. Our goal is identical to SFS, however, we tackle the problem by building a relationship between gradient of depth and intensity value at the corresponding location of image of the same object. This formula is simplified and approximated for handing different materials, lighting conditions and, the underneath sign matrix is also obtained by resizing/deforming Region of Interest(ROI) with respect to its counterpart of a similar object. The target object is then reconstructed from its still image. In addition to the process, delicate details of the surface is also rebuilt using a Gabor Wavelet Network(GWN) on different ROIs. Finally, for merging the patches together, a Self-Organizing Maps(SOM) based method is used to retrieve and smooth boundary parts of ROIs. Compared with state of art SFS based methods, the proposed method yields promising results on both widely used benchmark datasets and images in the wild.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Usually we prefer to use the principles of photometry to match the luminance of the grayscale image to the luminance of the original color image(in reality, RGB model has different weight combination as compared with YUV model) [13].
- 2.
This can be obtained by output of Heaviside function on difference of depth’s gradient.
- 3.
References
MPI-Inf 3d data. http://gvv.mpi-inf.mpg.de/files/
VAP dataset. http://www.vap.aau.dk/rgb-d-face-database/
Stanford 3d repository. http://graphics.stanford.edu/data/3Dscanrep/
Thingiverse. http://www.thingiverse.com/
UCF shape database. http://www.cs.ucf.edu/~vision/
RCA: RCA Electro-Optics Handbook, pp. 18–19, RCA (1974)
Horn, B.K.: Shape from shading. Doctoral Thesis MIT. MA, USA (1970)
Barron, J.T., Malik, J. : High-frequency shape and albedo from shading using natural image statistics. In: CVPR, pp. 2521–2528 (2011)
Horn, B.K., Brooks, M.J.: The variational approach to shape from shading. Comput. Vis. Gr. Image Process 33, 174–208 (1986)
Barron, J.T., Malik, J.: Shape, albedo, and illumination from a single image of an unknown object. In: CVPR, pp. 334–341 (2012)
Johnson, M.K., Adelson, E.H.: Shape estimation in natural illumination. In: CVPR, pp. 2553–2560 (2011)
Zhang, R., Tsai, P.-S., Cryer, J.E., Shah, M.: Shape from shading: a survey. IEEE Trans. PAMI 21, 690–706 (1999)
Volz, H.G.: Industrial Color Testing: Fundamentals and Techniques. Wiley-VCH, New York (2001)
Tsai, P.-S., Shah, M.: Shape from shading using linear approximation. Image Vis. Comput. 12, 487–498 (1994)
Han, Y., Lee, J-Y., Kweon, I.S.: High quality shape from a single RGB-D image under uncalibrated natural illumination. In: ICCV, pp. 1617–1624 (2013)
Woodham, R.J.: Photometric method for determining surface orientation from multiple images. Opt. Eng. 19, 139–144 (1980)
Yu, L.-F., Yeung, S.-K., Tai, Y.-W., Lin, S.: Shading-based shape refinement of RGB-D images. In: CVPR, pp. 1415–1422 (2013)
Bregler, C., Hertzmann, A., Biermann, H.: Recovering non-rigid 3d shape from image streams. In: CVPR, vol. 2, pp. 690–696 (2000)
Rusinkiewicz, S., Hall-Holt, O., Levoy, M.: Real-time 3d model acquisition. ACM Trans. Graph. 21, 438–446 (2002)
Liang, S., Kemelmacher-Shlizerman, I., Shapiro, L.G.: 3D face hallucination from a single depth frame. In: International Conference on 3D Vision (3DV) (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Yang, Z., Chandola, V. (2015). Surface Reconstruction from Intensity Image Using Illumination Model Based Morphable Modeling. In: Nalpantidis, L., Krüger, V., Eklundh, JO., Gasteratos, A. (eds) Computer Vision Systems. ICVS 2015. Lecture Notes in Computer Science(), vol 9163. Springer, Cham. https://doi.org/10.1007/978-3-319-20904-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-20904-3_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-20903-6
Online ISBN: 978-3-319-20904-3
eBook Packages: Computer ScienceComputer Science (R0)