AI帮你理解科学

AI 生成解读视频

AI抽取解析论文重点内容自动生成视频


pub
生成解读视频

AI 溯源

AI解析本论文相关学术脉络


Master Reading Tree
生成 溯源树

AI 精读

AI抽取本论文的概要总结


微博一下
We have proposed a novel method to separate diffuse and specular reflection components

Separating reflection components of textured surfaces using a single image.

IEEE Trans. Pattern Anal. Mach. Intell., no. 2 (2005): 178-193

被引用365|浏览22
WOS EI

摘要

In inhomogeneous objects, highlights are linear combinations of diffuse and specular reflection components. A number of methods have been proposed to separate or decompose these two components. To our knowledge, all methods that use a single input image require explicit color segmentation to deal with multicolored surfaces. Unfortunately,...更多

代码

数据

0
简介
  • SEPARATING diffuse and specular reflection components is an essential subject in the field of computer vision.
  • To properly acquire the diffuse only reflections, a method to separate the two components robustly and accurately is required.
  • When a bundle of light rays enters an inhomogeneous opaque surface, some of the rays will immediately reflect back into the air, while the remainder will penetrate the body of the object.
重点内容
  • SEPARATING diffuse and specular reflection components is an essential subject in the field of computer vision
  • Based on the dichromatic reflection model and chromaticities definitions derived above, we describe our goal: Given image intensities (IðxÞ) whose illumination chromaticity (À) is known, we intend to decompose them into their reflection components, mdðxÞÃðxÞ and msðxÞÀ
  • We have proposed a novel method to separate diffuse and specular reflection components
  • The main insight of the method is in the chromaticity-based iteration with regard to the logarithmic differentiation of the specular-free image
  • In specular-free images, specular reflection disappear should equal to m d (m s 1⁄4 of the
方法
  • Given a normalized image, a specular-free image is generated
  • Based on these two images, the “diffuse verification” verifies whether the normalized image has diffuse only pixels.
  • If it has diffuse only, the processes terminate.
  • The diffuse verification verifies once again whether the normalized image has diffuse-only pixels
  • These two processes are done iteratively until there is no specularity in the normalized image.
  • The following subsections will show the details of the two processes
结果
  • All images in the experiments were taken using a CCD camera: SONY DXC-9000 by setting the gamma correction off.
  • The authors used convex-shaped objects to avoid interreflections and did not take account of saturated or blooming pixels in the experiments.
  • The illumination chromaticities were estimated using a color constancy algorithm [26].
  • This color constancy method requires crude highlight regions, which can be obtained using thresholding in both intensity and saturation
结论
  • The authors assumed that the estimated illumination chromaticity is exactly identical to the input image’s illumination chromaticity, À 1⁄4 Àest (10).
  • The authors intend to describe the effect of illumination error in estimating the value of md by using the specular-to-diffuse mechanism.
  • Md of error illumination becomes: The authors express the medrrWe have proposed a novel method to separate diffuse and specular reflection components.
  • The main insight of the method is in the chromaticity-based iteration with regard to the logarithmic differentiation of the specular-free image.
  • Without requiring explicit color segmentation
  • It is possible because the authors base the method on local operation by utilizing the specular-free image.
  • The experimental results on complex textured images show the effectiveness of the proposed method
基金
  • This research was, in part, supported by Japan Science and Technology (JST) under CREST Ikeuchi Project
引用论文
  • R. Bajscy, S.W. Lee, and A. Leonardis, “Detection of Diffuse and Specular Interface Reflections by Color Image Segmentation,” Int’l J. Computer Vision, vol. 17, no. 3, pp. 249-272, 1996.
    Google ScholarLocate open access versionFindings
  • P. Beckmann and A. Spizzochino, The Scattering of Electromagnetic Waves from Rough Surfaces. New York: Pergamon, 1963.
    Google ScholarFindings
  • M. Born and E. Wolf, Principles of Optics, seventh ed. Cambridge, 1999.
    Google ScholarFindings
  • A. Criminisi, S.B. Kang, R. Swaminathan, S. Szeliski, and P. Anandan, “Extracting Layers and Analyzing Their Specular Properties Using Epipolar Plane Image Analysis,” Technical Report MSR-TR-2002-19, Microsoft Research, 2002.
    Google ScholarFindings
  • M. D’Zmura and P. Lennie, “Mechanism of Color Constancy,” J. Optics Soc. Am. A, vol. 3, no. 10, pp. 1162-1672, 1986.
    Google ScholarLocate open access versionFindings
  • B.V. Funt, M. Drew, and M. Brockington, “Recovering Shading from Color Images,” Proc. European Conf. Computer Vision (ECCV ’92), pp. 124-132, 1992.
    Google ScholarLocate open access versionFindings
  • R. Gershon, A.D. Jepson, and J.K. Tsotsos, “Ambient Illumination and the Determination of Material Changes,” J. Optics Soc. Am. A, vol. 3, no. 10, pp. 1700-1707, 1986.
    Google ScholarLocate open access versionFindings
  • R.C. Gonzales and R.E. Woods, Digital Image Processing. AddisonWesley, 1993.
    Google ScholarLocate open access versionFindings
  • G. Healey and R. Kondepudy, “Radiometric CCD Camera Calibration and Noise Estimation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 3, pp. 267-276, Mar. 1994.
    Google ScholarLocate open access versionFindings
  • J.M. Rubin and W.A. Richard, “Color Vision: Representing Material Categories,” AI Memo 764, MIT Artificial Intelligence Lab., 1984.
    Google ScholarFindings
  • G.J. Klinker, S.A. Shafer, and T. Kanade, “The Measurement of Highlights in Color Images,” Int’l J. Computer Vision, vol. 2, pp. 732, 1990.
    Google ScholarLocate open access versionFindings
  • J.H. Lambert, Photometria Sive de Mensura de Gratibus Luminis, Colorum et Umbrae. Augsberg, Germany: Eberhard Klett, 1760.
    Google ScholarFindings
  • H.C. Lee, E.J. Breneman, and C.P. Schulte, “Modeling Light Reflection for Computer Color Vision,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 4, pp. 402-409, Apr. 1990.
    Google ScholarLocate open access versionFindings
  • S.W. Lee, “Understanding of Surface Reflections in Computer Vision by Color and Multiple Views,” PhD thesis, Univ. of Pennsylvania, 1991.
    Google ScholarFindings
  • S.W. Lee and R. Bajcsy, “Detection of Specularity Using Color and Multiple Views,” Image and Vision Computing, vol. 10, pp. 643-653, 1992.
    Google ScholarLocate open access versionFindings
  • T.M. Lehmann and C. Palm, “Color Line Search for Illuminant Estimation in Real-World Scene,” J. Optics Soc. Am. A, vol. 18, no. 11, pp. 2679-2691, 2001.
    Google ScholarLocate open access versionFindings
  • S. Lin, Y. Li, S.B. Kang, X. Tong, and H.Y. Shum, “Diffuse-Specular Separation and Depth Recovery from Image Sequences,” Proc. European Conf. Computer Vision (ECCV ’02), pp. 210-224, 2002.
    Google ScholarLocate open access versionFindings
  • S. Lin and H.Y. Shum, “Separation of Diffuse and Specular Reflection in Color Images,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR ’01), 2001.
    Google ScholarLocate open access versionFindings
  • D. Miyazaki, R.T. Tan, K. Hara, and K. Ikeuchi, “PolarizationBased Inverse Rendering from a Single View,” Proc. IEEE Int’l Conf. Computer Vision (ICCV ’03), 2003.
    Google ScholarLocate open access versionFindings
  • S.K. Nayar, X.S. Fang, and T. Boult, “Separation of Reflection Components Using Color and Polarization,” Int’l J. Computer Vision, vol. 21, no. 3, 1996.
    Google ScholarLocate open access versionFindings
  • S.K. Nayar, K. Ikeuchi, and T. Kanade, “Surface Reflection: Physical and Geometrical Perspectives,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 7, pp. 611-634, July 1991.
    Google ScholarLocate open access versionFindings
  • M. Oren and S.K. Nayar, “Generalization of the Lambertian Model and Implications for Machine Vision,” Int’l J. Computer Vision, vol. 14, no. 3, pp. 227-251, 1995.
    Google ScholarLocate open access versionFindings
  • J.P.S. Parkkinen, J. Hallikainen, and T. Jasskelainen, “Characteristic Spectra of Munsell Colors,” J. Optics Soc. Am. A, vol. 6, 1989.
    Google ScholarLocate open access versionFindings
  • Y. Sato and K. Ikeuchi, “Temporal-Color Space Analysis of Reflection,” J. Optics Soc. Am. A, vol. 11, 1994.
    Google ScholarLocate open access versionFindings
  • S. Shafer, “Using Color to Separate Reflection Components,” Color Research and Applications, vol. 10, pp. 210-218, 1985.
    Google ScholarLocate open access versionFindings
  • R.T. Tan, K. Nishino, and K. Ikeuchi, “Color Constancy through Inverse Intensity Chromaticity Space,” J. Optics Soc. Am. A, vol. 21, no. 3, pp. 321-334, 2004.
    Google ScholarLocate open access versionFindings
  • R.T. Tan, K. Nishino, and K. Ikeuchi, “Separating Reflection Components Based on Chromaticity and Noise Analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 10, Oct. 2004.
    Google ScholarLocate open access versionFindings
  • K.E. Torrance and E.M. Sparrow, “Theory for Off-Specular Reflection from Roughened Surfaces,” J. Optics Soc. Am., vol. 57, pp. 1105-1114, 1966.
    Google ScholarLocate open access versionFindings
  • L. Wolff, S.K. Nayar, and M. Oren, “Improved Diffuse Reflection Models for Computer Vision,” Int’l J. Computer Vision, vol. 30, no. 1, pp. 55-71, 1998.
    Google ScholarLocate open access versionFindings
  • L.B. Wolff, “Polarization-Based Material Classification from Specular Reflection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 11, pp. 1059-1071, Nov. 1990.
    Google ScholarLocate open access versionFindings
  • L.B. Wolff, “A Diffuse Reflectance Model for Smooth Dielectrics,” J. Optics Soc. Am. A, vol. 11, no. 11, pp. 2956-2968, 1994.
    Google ScholarLocate open access versionFindings
  • L.B. Wolff and T. Boult, “Constraining Object Features Using Polarization Reflectance Model,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 7, pp. 635-657, July 1991. Robby T. Tan received the MS and PhD degrees in computer science from the University of Tokyo, Japan, in 2001 and 2004, respectively. Since May 2004, he has been a postdoctoral fellow at the Computer Vision (Ikeuchi) Laboratory, University of Tokyo, Japan. His research interests are in color constancy, intrinsic properties of images, spectral analysis, and the applications of optics in computer vision.
    Google ScholarLocate open access versionFindings
  • For more information on this or any other computing topic, please visit our Digital Library at www.computer.org/publications/dlib.
    Locate open access versionFindings
您的评分 :
0

 

标签
评论
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科