Abstract
Shadow removal is of significance in computer vision. Shadow usually adheres to texture, and it is difficult to decouple shadow from texture without any assumptions. In this paper, we suppose that the texture beneath shadow should bear the similar patterns, which makes the problem of simultaneously recovering the reflectance and light attenuation factor solvable with sole image. A novel shadow removal method is proposed, which is fulfilled by complementing the lost radiance in shadow region. Experiments show that our proposed approach could maintain the texture structure and the coherent lighting with the intact region.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Sato, I., Sato, Y., Ikeuchi, K.: Illumination from shadows. IEEE Trans. on PAMI 25(3), 290–300 (2003)
Goesele, M., Granier, X., Heidrich, W., Seidel, H.-P.: Accurate light source acquisition and rendering. In: Proc. of SIGGRAPH 2003 (2003)
Granier, X., Heidrich, W.: A simple layered RGB BRDF model. In: Proc. of Pacific Graphics 2002 (2002)
Cham, T.J., Rehg, J., Sukthankar, R., Sukthankar, G.: Shadow elimination and occluder light supression for multi-projector sisplays. In: Proc. of Computer Vision and Pattern Recognition (2003)
Jaynes, C., Webb, S., Steele, R.M.: Camera-based detection and removal of shadows from interactive multiprojector displays. IEEE Trans. on Visualization and Computer Graphics. 10(3), 290–301 (2004)
Hsieh, J.W., Hu, W.F., Chang, C.J., Chen, Y.S.: Shadow elimination for effective moving object detection by Gaussian shadow modeling. Image and Vision Computing 21(6), 505–516 (2003)
Debevec, P.E., Malik, J.: Recovering high dynamic range radiance maps from photographs. In: Proc. of SIGGRAPH 1997 (1997)
Martin, D.R., Fowlkes, C.C., Malik, J.: Learning to detect natural image boundaries using local brightness, bolor and texture cues. IEEE Trans. PAMI 26(5), 530–549 (2004)
Weiss, Y.: Deriving intrinsic images from image sequences. In: ICCV 2001 (2001)
Chuang, Y.Y., Goldman, D.B., Curless, B., Salesin, D.H., et al.: Shadow matting and compositing. In: Proc. of SIGRAPH 2003 (August 2003)
Rubner, Y., Tomasi, C.: Coalescing texture descriptors. In: Proc. ARPA Image Understanding Workshop (1996)
Nadimi, S., Bhanu, B.: Moving shadow detection using a physics-based approach. In: Proc. of Sixteen Intl. Conf. on Pattern Recognition, Canada, vol. 2, pp. 701–704 (2002)
Finlayson, G.D., Hordley, S.D., Drew, M.S.: Removing shadows from images. In: Proc. of Intl. Conf. Computer Vision 2001 (2001)
Finlayson, G.D., Drew, M.S., Lu, C.: Intrinsic images by entropy minimization. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3023, pp. 582–595. Springer, Heidelberg (2004)
Finlayson, G.D.: Coefficient color constancy. Ph.D. Dissertation of Simon Fraser Univ (April 1995)
Tan, R.T.: Illumination color and intrinsic surface properties - Physics-Based color analysis from a single image. Ph.D. Dissertation of Univ. of Tokyo (December 2003)
Liu, X., Hu, Y., Zhang, J., Tong, X., et al.: Synthesis and rendering of bidirectional texture functions on arbitrary surfaces. IEEE Trans. PAMI 10(3), 278–289 (2004)
Perez, P., Gangnet, M., Blake, A.: Poisson image editing. In: Proc. of SIGGRAPH 2003 (2003)
Drori, I., Choen-Or, D., Yeshurum, H.: Fragment-Based image completion. In: Proc. of SIGGRAPH 2003 (2003)
Bertalmio, M., Vese, L., Sapiro, G., Osher, S.: Simultaneous structure and texture image inpainting. IEEE Trans. on Image Processing 12(8), 882–889 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Du, Z., qin, X., Lin, H., Bao, H. (2005). Shadow Removal in Gradient Domain. In: Kamel, M., Campilho, A. (eds) Image Analysis and Recognition. ICIAR 2005. Lecture Notes in Computer Science, vol 3656. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11559573_14
Download citation
DOI: https://doi.org/10.1007/11559573_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29069-8
Online ISBN: 978-3-540-31938-2
eBook Packages: Computer ScienceComputer Science (R0)