Abstract
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 spurred by public datasets of ground truth data, such as the MIT Intrinsic Images dataset. However, the difficulty of acquiring ground truth data has meant that such datasets cover a small range of materials and objects. In contrast, real-world scenes contain a rich range of shapes and materials, lit by complex illumination.
In this paper we introduce Intrinsic Images in the Wild, a large-scale, public dataset for evaluating intrinsic image decompositions of indoor scenes. We create this benchmark through millions of crowdsourced annotations of relative comparisons of material properties at pairs of points in each scene. Crowdsourcing enables a scalable approach to acquiring a large database, and uses the ability of humans to judge material comparisons, despite variations in illumination. Given our database, we develop a dense CRF-based intrinsic image algorithm for images in the wild that outperforms a range of state-of-the-art intrinsic image algorithms. Intrinsic image decomposition remains a challenging problem; we release our code and database publicly to support future research on this problem, available online at http://intrinsic.cs.cornell.edu/.
Supplemental Material
Available for Download
Supplemental material.
- Adams, A., Baek, J., and Davis, A. 2010. Fast high-dimensional filtering using the permutohedral lattice. Computer Graphics Forum (Eurographics) 29, 2.Google ScholarCross Ref
- Barron, J. T., and Malik, J. 2012. Color constancy, intrinsic images, and shape estimation. In Proc. European Conference on Computer Vision. Google ScholarDigital Library
- Barron, J. T., and Malik, J. 2012. Shape, albedo, and illumination from a single image of an unknown object. In Proc. Computer Vision and Pattern Recognition. Google ScholarDigital Library
- Barron, J. T., and Malik, J. 2013. Intrinsic scene properties from a single RGB-D image. In Proc. Computer Vision and Pattern Recognition. Google ScholarDigital Library
- Barron, J. T., and Malik, J. 2013. Shape, illumination, and reflectance from shading. Tech. rep., UC Berkeley.Google Scholar
- Bell, S., Upchurch, P., Snavely, N., and Bala, K. 2013. OpenSurfaces: A richly annotated catalog of surface appearance. ACM Trans. on Graphics (SIGGRAPH) 32, 4. Google ScholarDigital Library
- Bostock, M., 2013. D3. http://d3js.org/. {Online; accessed 24-Mar-2014}.Google Scholar
- Bousseau, A., Paris, S., and Durand, F. 2009. User-assisted intrinsic images. ACM Trans. on Graphics (SIGGRAPH Asia) 28, 5. Google ScholarDigital Library
- Boyadzhiev, I., Paris, S., and Bala, K. 2013. User-assisted image compositing for photographic lighting. ACM Trans. on Graphics (SIGGRAPH) 32, 4. Google ScholarDigital Library
- Branson, S., Wah, C., Babenko, B., Schroff, F., Welinder, P., Perona, P., and Belongie, S. 2010. Visual recognition with humans in the loop. In Proc. European Conference on Computer Vision. Google ScholarDigital Library
- Carroll, R., Ramamoorthi, R., and Agrawala, M. 2011. Illumination decomposition for material recoloring with consistent interreflections. ACM Trans. on Graphics (SIGGRAPH). Google ScholarDigital Library
- Chen, Q., and Koltun, V. 2013. A simple model for intrinsic image decomposition with depth cues. In Proc. International Conference on Computer Vision. Google ScholarDigital Library
- Cole, F., Sanik, K., DeCarlo, D., Finkelstein, A., Funkhouser, T., Rusinkiewicz, S., and Singh, M. 2009. How well do line drawings depict shape? ACM Trans. on Graphics (SIGGRAPH) 28, 3. Google ScholarDigital Library
- Dawid, A. P., and Skene, A. M. 1979. Maximum likelihood estimation of observer error-rates using the EM algorithm. In J. Roy. Statistical Society.Google Scholar
- Felzenszwalb, P., McAllester, D., and Ramanan, D. 2008. A discriminatively trained, multiscale, deformable part model. In Proc. Computer Vision and Pattern Recognition.Google Scholar
- Garces, E., Munoz, A., Lopez-Moreno, J., and Gutierrez, D. 2012. Intrinsic images by clustering. Computer Graphics Forum (Eurographics Symposium on Rendering) 31, 4. Google ScholarDigital Library
- Gehler, P., Rother, C., Kiefel, M., Zhang, L., and Scholkopf, B. 2011. Recovering intrinsic images with a global sparsity prior on reflectance. In Neural Information Processing Systems.Google Scholar
- Gingold, Y., Shamir, A., and Cohen-Or, D. 2012. Micro perceptual human computation. ACM Trans. on Graphics 31, 5. Google ScholarDigital Library
- Grosse, R., Johnson, M. K., Adelson, E. H., and Freeman, W. T. 2009. Ground truth dataset and baseline evaluations for intrinsic image algorithms. In Proc. International Conference on Computer Vision.Google Scholar
- Haber, T., Fuchs, C., Bekaer, P., Seidel, H.-P., Goesele, M., and Lensch, H. P. 2009. Relighting objects from image collections. In Proc. Computer Vision and Pattern Recognition.Google Scholar
- Hauagge, D., Wehrwein, S., Bala, K., and Snavely, N. 2013. Photometric ambient occlusion. Proc. Computer Vision and Pattern Recognition. Google ScholarDigital Library
- Krähenbühl, P., and Koltun, V. 2011. Efficient inference in fully connected CRFs with gaussian edge potentials. In Neural Information Processing Systems.Google Scholar
- Krähenbühl, P., and Koltun, V. 2013. Parameter learning and convergent inference for dense random fields. In Proc. International Conference on Machine Learning.Google Scholar
- Laffont, P.-Y., Bousseau, A., Paris, S., Durand, F., and Drettakis, G. 2012. Coherent intrinsic images from photo collections. ACM Trans. on Graphics (SIGGRAPH Asia) 31, 6. Google ScholarDigital Library
- Laffont, P., Bousseau, A., and Drettakis, G. 2013. Rich intrinsic image decomposition of outdoor scenes from multiple views. IEEE Trans. on Visualization and Computer Graphics 19, 2. Google ScholarDigital Library
- Land, E. H., and McCann, J. J. 1971. Lightness and retinex theory. J. Opt. Soc. Am. 61, 1.Google ScholarCross Ref
- Liao, Z., Rock, J., Wang, Y., and Forsyth, D. 2013. Non-parametric filtering for geometric detail extraction and material representation. In Proc. Computer Vision and Pattern Recognition. Google ScholarDigital Library
- Liu, X., Jiang, L., Wong, T.-T., and Fu, C.-W. 2012. Statistical invariance for texture synthesis. IEEE Trans. on Visualization and Computer Graphics 18, 11. Google ScholarDigital Library
- Oh, B. M., Chen, M., Dorsey, J., and Durand, F. 2001. Image-based modeling and photo editing. In Proc. Conference on Comp. Graphics and Interactive Techniques (SIGGRAPH). Google ScholarDigital Library
- Omer, I., and Werman, M. 2004. Color lines: image specific color representation. In Proc. Computer Vision and Pattern Recognition. Google ScholarDigital Library
- Ostrovsky, Y., Cavanagh, P., and Sinha, P. 2005. Perceiving illumination inconsistencies in scenes. Perception 34, 11.Google ScholarCross Ref
- Rubinstein, M., Gutierrez, D., Sorkine, O., and Shamir, A. 2010. A comparative study of image retargeting. ACM Trans. on Graphics (SIGGRAPH Asia) 29, 6. Google ScholarDigital Library
- Shen, L., and Yeo, C. 2011. Intrinsic images decomposition using a local and global sparse representation of reflectance. In Proc. Computer Vision and Pattern Recognition. Google ScholarDigital Library
- Shen, L., Tan, P., and Lin, S. 2008. Intrinsic image decomposition with non-local texture cues. In Proc. Computer Vision and Pattern Recognition.Google Scholar
- Shen, J., Yang, X., Jia, Y., and Li, X. 2011. Intrinsic images using optimization. In Proc. Computer Vision and Pattern Recognition. Google ScholarDigital Library
- Tappen, M., Freeman, W., and Adelson, E. 2005. Recovering intrinsic images from a single image. IEEE Trans. on Pattern Analysis and Machine Intelligence. Google ScholarDigital Library
- Tappen, M. F., Adelson, E. H., and Freeman, W. T. 2006. Estimating intrinsic component images using non-linear regression. In Proc. Computer Vision and Pattern Recognition. Google ScholarDigital Library
- van Wijk, J. J., and Nuij, W. A. 2003. Smooth and efficient zooming and panning. In Proc. IEEE Conference on Information Visualization (INFOVIS). Google ScholarDigital Library
- Weiss, Y. 2001. Deriving intrinsic images from image sequences. In Proc. International Conference on Computer Vision.Google ScholarCross Ref
- Welinder, P., Branson, S., Belongie, S., and Perona, P. 2010. The multidimensional wisdom of crowds. In Neural Information Processing Systems.Google Scholar
- Zhao, Q., Tan, P., Dai, Q., Shen, L., Wu, E., and Lin, S. 2012. A closed-form solution to retinex with nonlocal texture constraints. IEEE Trans. on Pattern Analysis and Machine Intelligence 34, 7. Google ScholarDigital Library
Index Terms
- Intrinsic images in the wild
Recommendations
An L1 image transform for edge-preserving smoothing and scene-level intrinsic decomposition
Identifying sparse salient structures from dense pixels is a longstanding problem in visual computing. Solutions to this problem can benefit both image manipulation and understanding. In this paper, we introduce an image transform based on the L1 norm ...
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 ...
Recovering Intrinsic Images from a Single Image
Interpreting real-world images requires the ability distinguish the different characteristics of the scene that lead to its final appearance. Two of the most important of these characteristics are the shading and reflectance of each point in the scene. ...
Comments