Skip to main content
SpringerLink
Log in

Image Relighting by Analogy

  • Conference paper
Advances in Visual Computing (ISVC 2011)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 6938))

Included in the following conference series:

Abstract

We propose and analyze an example-based framework for relighting images. In this framework, there are a number of images of reference objects captured under different illumination conditions. Given an input image of a new object captured under one of the previously observed illumination conditions, new images can be synthesized for the input object under all the other illumination conditions that are present in the reference images. It does not require any other prior knowledge on the reference and target objects, except that they share the same albedo. Though it is appreciated if the reference objects have similar shape as the target object, sphere or ellipsoid which has plenty of local geometry samples are sufficient to build up a look-up table, as this method solves the problem locally. Gradient domain methods are introduced to finally generate visual-pleasing results. We demonstrate this framework on synthesized data and real images.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: From few to many: Illumination cone models for face recognition under variable lighting and pose. TPAMI 23, 643–660 (2001)

    Article  Google Scholar 

  2. Adini, Y., Moses, Y., Ullman, S.: Face recognition: The problem of compensating for changes in illumination direction. TPAMI 19, 721–732 (1997)

    Article  Google Scholar 

  3. Pighin, F.H., Szeliski, R., Salesin, D.: Resynthesizing facial animation through 3d model-based tracking. In: ICCV, Kerkyra, Greece, pp. 143–150 (1999)

    Google Scholar 

  4. Basso, A., Graf, H.P., Gibbon, D.C., Cosatto, E., Liu, S.: Virtual light: digitally-generated lighting for video conferencing applications. In: ICIP, Thessaloniki, Greece, pp. 1085–1088 (2001)

    Google Scholar 

  5. Wen, Z., Liu, Z., Huang, T.S.: Face relighting with radiance environment maps. In: CVPR, Madison, WI, USA, vol. 2, pp. 158–165 (2003)

    Google Scholar 

  6. Fuchs, M., Blanz, V., Lensch, H.P.A., Seidel, H.P.: Reflectance from images: A model-based approach for human faces. TVCG 11, 296–305 (2005)

    Google Scholar 

  7. Okabe, M., Zeng, G., Matsushita, Y., Igarashi, T., Quan, L., Shum, H.Y.: Single-view relighting with normal map painting. In: Pacific Graphics, Taipei, Taiwan, pp. 27–34 (2006)

    Google Scholar 

  8. Fuchs, M., Blanz, V., Seidel, H.P.: Bayesian relighting. In: EGSR, Konstanz, Germany, pp. 157–164 (2005)

    Google Scholar 

  9. Debevec, P.E., Hawkins, T., Tchou, C., Duiker, H.P., Sarokin, W., Sagar, M.: Acquiring the reflectance field of a human face. In: SIGGRAPH, New Orleans, LA, USA, pp. 145–156 (2000)

    Google Scholar 

  10. Masselus, V., Peers, P., Dutré, P., Willems, Y.D.: Smooth reconstruction and compact representation of reflectance functions for image-based relighting. In: EGSR, Norrköping, Swede, pp. 287–298 (2004)

    Google Scholar 

  11. Shashua, A., Riklin-Raviv, T.: The quotient image: Class-based re-rendering and recognition with varying illuminations. TPAMI 23, 129–139 (2001)

    Article  Google Scholar 

  12. Zhang, L., Wang, S., Samaras, D.: Face synthesis and recognition from a single image under arbitrary unknown lighting using a spherical harmonic basis morphable model. In: CVPR, San Diego, CA, USA, vol. 2, pp. 209–216 (2005)

    Google Scholar 

  13. Peers, P., Tamura, N., Matusik, W., Debevec, P.E.: Post-production facial performance relighting using reflectance transfer. TOG 26, 52 (2007)

    Article  Google Scholar 

  14. Hertzmann, A., Jacobs, C.E., Oliver, N., Curless, B., Salesin, D.: Image analogies. In: SIGGRAPH, Los Angels, CA, USA, pp. 327–340 (2001)

    Google Scholar 

  15. Lee, C.H., Rosenfeld, A.: Improved methods of estimating shape from shading using the light source coordinate system. Artificial Intelligence 26, 125–143 (1985)

    Article  MathSciNet  MATH  Google Scholar 

  16. Frankot, R.T., Chellappa, R.: A method for enforcing integrability in shape from shading algorithms. TPAMI 10, 439–451 (1988)

    Article  MATH  Google Scholar 

  17. Land, E.H., McCann, J.J.: Lightness and retinex theory. JOSA 61, 1–11 (1971)

    Article  Google Scholar 

  18. Bhat, P., Curless, B., Cohen, M.F., Zitnick, C.L.: Fourier analysis of the 2d screened poisson equation for gradient domain problems. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 114–128. Springer, Heidelberg (2008)

    Chapter  Google Scholar 

  19. Muja, M., Lowe, D.G.: Fast approximate nearest neighbors with automatic algorithm configuration. In: VISAPP, Lisbon, Portugal, pp. 331–340 (2009)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Centre for Multimedia and Network Technology, School of Computer Engineering, Nanyang Technological University, Singapore

    Xiao Teng & Tat-Jen Cham

Authors
  1. Xiao Teng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tat-Jen Cham
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. University of Nevada, 89557, Reno, NV, USA

    George Bebis

  2. NASA Ames Research Center, 94035, Moffett Field, CA, USA

    Richard Boyle

  3. Lawrence Berkeley National Laboratory, 94720, Berkeley, CA, USA

    Bahram Parvin

  4. Desert Research Institute, 89512, Reno, NV, USA

    Darko Koracin

  5. Department of Computer Science and Engineering, University of South Carolina, 29208, Columbia, SC, USA

    Song Wang

  6. HRL Laboratories, 3011 Malibu Canyon Road, 90265-4797, Malibu, CA, USA

    Kim Kyungnam

  7. Purdue University, 47907-2021, West Lafayette, IN, USA

    Bedrich Benes

  8. Sandia National Laboratory, 87185, Albuquerque, NM, USA

    Kenneth Moreland

  9. University of Louisiana, 70504, Lafayette, LA, USA

    Christoph Borst

  10. Adobe Systems Incorporated, San Francisco, CA, USA

    Stephen DiVerdi

  11. Polytechnic Institute of NYU, 11201, Brooklyn, NY, USA

    Chiang Yi-Jen

  12. Lawrence Livermore National Laboratory, 94551-0808, Livermore, CA, USA

    Jiang Ming

Rights and permissions

Reprints and permissions

Copyright information

© 2011 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Teng, X., Cham, TJ. (2011). Image Relighting by Analogy. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2011. Lecture Notes in Computer Science, vol 6938. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24028-7_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-24028-7_8

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-24027-0

  • Online ISBN: 978-3-642-24028-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation