Abstract
A large photo collection downloaded from the internet spans a wide range of scenes, cameras, and photographers. In this paper we introduce several novel priors for statistics of such large photo collections that are independent of these factors. We then propose that properties of these factors can be recovered by examining the deviation between these statistical priors and the statistics of a slice of the overall photo collection that holds one factor constant. Specifically, we recover the radiometric properties of a particular camera model by collecting numerous images captured by it, and examining the deviation of this collection’s statistics from that of a broader photo collection whose camera-specific effects have been removed. We show that using this approach we can recover both a camera model’s non-linear response function and the spatially-varying vignetting of the camera’s different lens settings. All this is achieved using publicly available photographs, without requiring images captured under controlled conditions or physical access to the cameras. We also apply this concept to identify bad pixels on the detectors of specific camera instances. We conclude with a discussion of future applications of this general approach to other common computer vision problems.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Snavely, N., Seitz, S.M., Szeliski, R.: Photo tourism: Exploring photo collections in 3D. ACM Transactions on Graphics (SIGGRAPH), 835–846 (2006)
Goesele, M., Snavely, N., Curless, B., Hoppe, H., Seitz, S.M.: Multi-View Stereo for Community Photo Collections. In: ICCV (2007)
Hays, J., Efros, A.A.: Scene Completion Using Millions of Photographs. ACM Transactions on Graphics (SIGGRAPH) (2007)
Lalonde, J.-F., Hoiem, D., Efros, A.A., Rother, C., Winn, J., Criminisi, A.: Photo Clip Art. ACM Transactions on Graphics (SIGGRAPH) (2007)
Torralba, A., Fergus, R., Freeman, W.: Tiny Images. MIT Tech Report (2007)
Olshausen, B.A., Field, D.J.: Emergence of simple-cell receptive field properties by learning a sparse code for nature images. In: Nature, pp. 607–609 (1996)
Simoncelli, E.: Statistical Models for Images: Compression, Restoration and Synthesis. In: Asilomar Conference on Signals, Systems and Computers, pp. 673–678 (1997)
Switkes, E., Mayer, M.J., Sloan, J.A.: Spatial frequency analysis of the visual environment: anisotropy and the carpentered environment hypothesis. Vision Research, 1393–1399 (1978)
Baddeley, R.: The Correlational Structure of Natural Images and the Calibration of Spatial Representations. Cognitive Science, 351–372 (1997)
Burton, G.J., Moorhead, I.R.: Color and spatial structure in natural scenes. Applied Optics, 157–170 (1987)
Field, D.: Relations between the statistics of natural images and the response properties of cortical cells. J. of the Optical Society of America, 2379–2394 (1987)
Wackrow, R., Chandler, J.H., Bryan, P.: Geometric consistency and stability of consumer-grade digital cameras for accurate spatial measurement. The Photogrammetric Record, 121–134 (2007)
DxO Labs: www.dxo.com
PTLens: www.epaperpress.com/ptlens
Weiss, Y.: Deriving intrinsic images from image sequences. In: ICCV, pp. 68–75 (2001)
Tappen, M.F., Russell, B.C., Freeman, W.T.: Exploiting the sparse derivative prior for super-resolution and image demosaicing. In: Workshop on Statistical and Computational Theories of Vision (2003)
Fergus, R., Singh, B., Hertzmann, A., Roweis, S.T., Freeman, W.T.: Removing Camera Shake From A Single Photograph. SIGGRAPH, 787–794 (2006)
Torralba, A., Oliva, A.: Statistics of Natural Images Categories. Network: Computation in Neural Systems 14, 391–412 (2003)
Debevec, P.E., Malik, J.: Recovering high dynamic range radiance maps from photographs. SIGGRAPH, 369–378 (1997)
Mitsunaga, T., Nayar, S.K.: Radiometric self calibration. CVPR, 1374–1380 (1999)
Grossberg, M.D., Nayar, S.K.: Determining the Camera Response from Images: What is Knowable?. PAMI, 1455–1467 (2003)
Manders, C., Aimone, C., Mann, S.: Camera response function recovery from different illuminations of identical subject matter. ICIP, 2965–2968 (2004)
Farid, H.: Blind Inverse Gamma Correction. IEEE Transactions on Image Processing, 1428–1433 (2001)
Lin, S., Gu, J., Yamazaki, S., Shum, H.-Y.: Radiometric Calibration Using a Single Image. CVPR, 938–945 (2004)
Sawchuk, A.: Real-time correction of intensity nonlinearities in imaging systems. IEEE Transactions on Computers, 34–39 (1977)
Kang, S.B., Weiss, R.: Can we calibrate a camera using an image of a flat textureless lambertian surface? In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 640–653. Springer, Heidelberg (2000)
Stumpfel, J., Jones, A., Wenger, A., Debevec, P.: Direct HDR capture of the sun and sky. Afrigraph, 145–149 (2004)
Goldman, D.B., Chen, J.H.: Vignette and exposure calibration and compensation. In: ICCV, pp. 899–906 (2005)
Litvinov, A., Schechner, Y.Y.: Addressing radiometric nonidealities: A unified framework. CVPR, 52–59 (2005)
Jia, J., Tang, C.K.: Tensor voting for image correction by global and local intensity alignment. IEEE Transactions PAMI 27(1), 36–50 (2005)
Zheng, Y., Lin, S., Kang, S.B.: Single-Image Vignetting Correction. CVPR (2006)
Dudas, J., Jung, C., Wu, L., Chapman, G.H., Koren, I., Koren, Z.: On-Line Mapping of In-Field Defects in Image Sensor Arrays. In: International Symposium on Defect and Fault-Tolerance in VLSI Systems, pp. 439–447 (2006)
Press, W., Teukolsky, S., Vetterling, W., Flannery, B.: Numerical Recipes in C: The Art of Scientific Computing (1992)
Grossberg, M.D., Nayar, S.K.: What is the Space of Camera Response Functions?. CVPR, 602–609 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kuthirummal, S., Agarwala, A., Goldman, D.B., Nayar, S.K. (2008). Priors for Large Photo Collections and What They Reveal about Cameras. In: Forsyth, D., Torr, P., Zisserman, A. (eds) Computer Vision – ECCV 2008. ECCV 2008. Lecture Notes in Computer Science, vol 5305. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88693-8_6
Download citation
DOI: https://doi.org/10.1007/978-3-540-88693-8_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88692-1
Online ISBN: 978-3-540-88693-8
eBook Packages: Computer ScienceComputer Science (R0)