Abstract
For many computational photography applications, the lighting and materials in the scene are critical pieces of information. We seek to obtain intrinsic images, which decompose a photo into the product of an illumination component that represents lighting effects and a reflectance component that is the color of the observed material. This is an under-constrained problem and automatic methods are challenged by complex natural images. We describe a new approach that enables users to guide an optimization with simple indications such as regions of constant reflectance or illumination. Based on a simple assumption on local reflectance distributions, we derive a new propagation energy that enables a closed form solution using linear least-squares. We achieve fast performance by introducing a novel downsampling that preserves local color distributions. We demonstrate intrinsic image decomposition on a variety of images and show applications.
Supplemental Material
Available for Download
- Agrawal, A., Raskar, R., and Chellappa, R. 2006. Edge suppression by gradient field transformation using cross-projection tensors. In CVPR, 2301--2308. Google ScholarDigital Library
- Barrow, H., and Tenenbaum, J. 1978. Recovering intrinsic scene characteristics from images. Computer Vision Systems.Google Scholar
- Briggs, W. L., Henson, V. E., and McCormick, S. F. 2000. A multigrid tutorial (2nd ed.). Society for Industrial and Applied Mathematics. Google ScholarDigital Library
- Buatois, L., Caumon, G., and Lévy, B. 2007. Concurrent number cruncher: An efficient sparse linear solver on the gpu. In High Performance Computation Conference. Google ScholarDigital Library
- Chuang, Y.-Y., Curless, B., Salesin, D. H., and Szeliski, R. 2001. A bayesian approach to digital matting. In CVPR.Google Scholar
- Fang, H., and Hart, J. C. 2004. Textureshop: Texture synthesis as a photograph editing tool. ACM TOG (proc. of SIGGRAPH 2004) 23, 3, 354--359. Google ScholarDigital Library
- Fattal, R. 2008. Single image dehazing. ACM TOG (proc. of SIGGRAPH 2008) 27, 3, 72. Google ScholarDigital Library
- Finlayson, G. D., Hordley, S. D., and Drew, M. S. 2002. Removing shadows from images. In ECCV. Google ScholarDigital Library
- Finlayson, G. D., Drew, M. S., and Lu, C. 2004. Intrinsic images by entropy minimization. In ECCV, 582--595.Google Scholar
- Horn, B. K. 1986. Robot Vision. MIT Press. Google ScholarDigital Library
- Hsu, E., Mertens, T., Paris, S., Avidan, S., and Durand, F. 2008. Light mixture estimation for spatially varying white balance. ACM TOG (proc. of SIGGRAPH 2008) 27, 3, 70. Google ScholarDigital Library
- Khan, E., Reinhard, E., Fleming, R., and Bülthoff, H. 2005. Image-based material editing. ACM TOG (proc. of SIGGRAPH 2005) 24, 3, 654--663. Google ScholarDigital Library
- Land, E. H., and McCann, J. J. 1971. Lightness and retinex theory. Journal of the optical society of America 61, 1.Google ScholarCross Ref
- Levin, A., and Weiss, Y. 2007. User assisted separation of reflections from a single image using a sparsity prior. IEEE Trans. PAMI 29, 9, 1647--1654. Google ScholarDigital Library
- Levin, A., Lischinski, D., and Weiss, Y. 2004. Colorization using optimization. ACM TOG (proc. of SIGGRAPH 2004) 23, 689--694. Google ScholarDigital Library
- Levin, A., Lischinski, D., and Weiss, Y. 2008. A closed-form solution to natural image matting. IEEE Trans. PAMI. Google ScholarDigital Library
- Liu, X., Wan, L., Qu, Y., Wong, T.-T., Lin, S., Leung, C.-S., and Heng, P.-A. 2008. Intrinsic colorization. ACM TOG (proc. of SIGGRAPH Asia 2008) 27, 5, 152. Google ScholarDigital Library
- McCann, J., and Pollard, N. S. 2008. Real-time gradient-domain painting. ACM TOG (Proc. of SIGGRAPH) 27, 3, 93. Google ScholarDigital Library
- Mohan, A., Tumblin, J., and Choudhury, P. 2007. Editing soft shadows in a digital photograph. IEEE Computer Graphics and Applications 27, 2, 23--31. Google ScholarDigital Library
- Omer, I., and Werman, M. 2004. Color lines: Image specific color representation. In CVPR, 946--953. Google ScholarDigital Library
- Shen, L., Tan, P., and Lin, S. 2008. Intrinsic image decomposition with non-local texture cues. In CVPR.Google Scholar
- Shor, Y., and Lischinski, D. 2008. The shadow meets the mask: Pyramid-based shadow removal. Computer Graphics Forum (Proc. of Eurographics) 27, 3.Google ScholarCross Ref
- Sinha, P., and Adelson, E. 1993. Recovering reflectance and illumination in a world of painted polyhedra. In ICCV, 156--163.Google Scholar
- Tappen, M. F., Freeman, W. T., and Adelson, E. H. 2005. Recovering intrinsic images from a single image. IEEE Trans. PAMI 27, 9. Google ScholarDigital Library
- Weiss, Y. 2001. Deriving intrinsic images from image sequences. In ICCV, 68--75.Google Scholar
- Wu, T.-P., Tang, C.-K., Brown, M. S., and Shum, H.-Y. 2007. Natural shadow matting. ACM TOG 26, 2, 8. Google ScholarDigital Library
- Yu, Y., and Malik, J. 1998. Recovering photometric properties of architectural scenes from photographs. In ACM SIGGRAPH 98, 207--217. Google ScholarDigital Library
Index Terms
- User-assisted intrinsic images
Recommendations
Intrinsic images in the wild
Intrinsic image decomposition separates an image into a reflectance layer and a shading layer. Automatic intrinsic image decomposition remains a significant challenge, particularly for real-world scenes. Advances on this longstanding problem have been ...
User-assisted intrinsic images
SIGGRAPH Asia '09: ACM SIGGRAPH Asia 2009 papersFor many computational photography applications, the lighting and materials in the scene are critical pieces of information. We seek to obtain intrinsic images, which decompose a photo into the product of an illumination component that represents ...
Multiview Intrinsic Images of Outdoors Scenes with an Application to Relighting
We introduce a method to compute intrinsic images for a multiview set of outdoor photos with cast shadows, taken under the same lighting. We use an automatic 3D reconstruction from these photos and the sun direction as input and decompose each image ...
Comments