S.K. Nayar and S.G. Narasimhan, "Vision in Bad Weather," Proc. Seventh Int'l Conf. Computer Vision, 1999. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Three-Dimensional Reconstruction of Fire from Images - Hasinoff (2002) (1 citation) (Correct)
....e ects of atmospheric phenomena on image formation. Similarly, most image formation models of re (see x2.3) assume smokeless conditions or consider the e ect of smoke separately. Nayar and Narasimhan have proposed that the e ects of bad weather should be considered when designing vision systems [80, 79]. Moreover, they describe how bad weather conditions might even be turned to an advantage, if we take the view that the 4.5. Vision in Bad Weather 53 atmosphere acts to modulate information about the scene. They describe algorithms that estimate additional information about the scene, such as ....
....relatively una ected by a uniform blanket of thin smoke, but more upset by thicker and heterogeneous smoke. Using multiple images of the same scene taken under di erent weather conditions, relative depths of point light sources can be estimated by comparing the degree of attenuation in the images [80]. If the images are taken at night, illumination from the environment is negligible and a simple scattering model suces. The optical thicknesses of the di erent weather conditions can then be easily computed in order to estimate the relative depths. Another technique involves estimating relative ....
[Article contains additional citation context not shown here]
S. Nayar and S. Narasimhan. Vision in bad weather. In Proc. IEEE International Conference On Computer Vision 1999.
Appearance-based 3-D Face Recognition from Video - Krüger, Gross, Baker (2002) (Correct)
....of light in free space. It is a 5D function of position (3D) and orientation (2D) In addition, it is also sometimes modeled as a function of time, wavelength, and polarization, depending on the application in mind. Assuming that there is no absorption or scattering of light through the air [14], the light field is actually only a 4D function, a 2D function of position defined over a 2D surface, and a 2D function of direction [3; 10] In 2D, the light field of a 2D object is actually 2D rather, than the 3D that might be expected. See Figure 1,left, for an illustration. 3.2 Eigen ....
S.K. Nayar and S. Narasimhan. Vision in bad weather. In Korfu, Greece, 1999.
When is the Shape of a Scene Unique Given its Light-Field.. - Baker, Sim, Kanade (2002) (2 citations) (Correct)
....based on its wavelength or polarization, and (2) there is an implicit assumption in stereo that the images are captured at the same time, or equivalently that the scene and illumination do not change. Assuming that there is no absorption, scattering, or emission of light through the air [Nayar and Narasimhan, 1999] , the light field is only a 4D function, a function of direction (2D) defined on a (2D) surface [Gortler et al. 1996, Levoy and Hanrahan, 1996] Similarly, the lightfield of a 2D scene is 2D rather than 3D, as illustrated in Figure 1. We make the no absorp2 ....
S.K. Nayar and S.G. Narasimhan. Vision in bad weather. In Proceedings of the 7th International Conference on Computer Vision, 1999.
Eigen Light-Fields and Face Recognition Across Pose - Gross, Matthews, Baker (2002) (6 citations) (Correct)
....this paper for ease of explanation. 5D function of position (3D) and orientation (2D) In addition, it is also sometimes modeled as a function of time, wavelength, and polarization, depending on the application in mind. Assuming that there is no absorption or scattering of light through the air [11], the light field is actually only a 4D function, a 2D function of position defined over a 2D surface, and a 2D function of direction [7, 9] In 2D, the light field of a 2D object is actually 2D rather, than the 3D that might be expected. See Figure 1 for an illustration. 2.2. Eigen Light Fields ....
S. Nayar and S. Narasimhan. Vision in bad weather. In Proc. 7th ICCV, 1999.
A Characterization of Inherent Stereo Ambiguities - Baker, Sim, Kanade (2001) (3 citations) (Correct)
....(and need not even be connected. or polarization, and (2) there is an implicit assumption in stereo that the images are captured at the same time, or equivalently that the scene and illumination do not change. Assuming there is no absorption, scattering, or emission of light through the air [14] , the light field is only a 4D function, a function of 2D direction defined on a 2D surface [7, 12] Similarly, the light field of a 2D scene is 2D rather than 3D, as illustrated in Figure 1. We make the no absorption assumption in this paper, and also, for ease of explanation, assume that ....
S. Nayar and S. Narasimhan. Vision in bad weather. In Proc. of the 7th IEEE Intl. Conf. on Computer Vision, 1999.
Computing Optical Flow with Physical Models of Brightness.. - Haußecker, Fleet (Correct)
....flow field. Although studied extensively [1, 11] reliable optical flow computation still remains difficult in many cases. Problems arise from the complex physical processes involved in scene illumination, surface reflection, and the transmission of radiation through surfaces and the atmosphere [12, 24, 19]. Without a model of image formation it is not possible to unambiguously relate spatiotemporal brightness to motion. # Part of this work was performed while HWH was with the Interdisciplinary Center for Scientific Computing, Heidelberg University, Germany. Portions of this work were supported ....
....With only two frames, one can only model brightness changes that are linear in time. 2 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Hilton Head Island, SC, June 2000 If brightness is not conserved, then the optical flow field estimated from (2) can be severely biased [4, 17, 18, 24, 3, 20, 9, 19]. Causes of brightness variation include moving illumination envelopes, changing orientation of surfaces under directional illumination, and atmospheric influences in outdoor applications. Other instances occur in scientific applications that quantitatively investigate dynamic processes [13] ....
S. K. Nayar and G. Narasimhan. Vision in bad weather. Proc. IEEE ICCV, pp. 820--827, Corfu, 1999.
Contrast Restoration of - Weather Degraded Images Self-citation (Nayar Narasimhan) (Correct)
No context found.
S.K. Nayar and S.G. Narasimhan, "Vision in Bad Weather," Proc. Seventh Int'l Conf. Computer Vision, 1999.
Chromatic Framework for Vision in Bad Weather - Srinivasa Narasimhan And (2000) (5 citations) Self-citation (Nayar Narasimhan) (Correct)
No context found.
S.K. Nayar and S.G. Narasimhan. Vision in bad weather. Proceedings of the 7th International Conference on Computer Vision, 1999.
International Journal of Computer Vision 48(3), 233--254, 2002 - Vision And The (1989) (3 citations) Self-citation (Nayar Narasimhan) (Correct)
No context found.
Nayar, S.K. and Narasimhan, S.G. 1999. Vision in bad weather. In Proceedings of the 7th International Conference on Computer Vision.
Gradient Domain Context Enhancement For Fixed Cameras - Adrian Ilie Department (2004) (Correct)
No context found.
Nayar S.K. and Narasimhan S.G., "Vision in Bad Weather," in Proceedings of ICCV, 1999, pp. 820-- 827.
Three-Dimensional Reconstruction of Fire from Images - Hasinoff (2002) (1 citation) (Correct)
No context found.
S. Nayar and S. Narasimhan. Vision in bad weather. In Proc. IEEE International Conference On Computer Vision 1999.
Obstacle Detection and Terrain Classification for.. - Manduchi.. (2004) (2 citations) (Correct)
No context found.
S.K. Nayar and S.G. Narasimhan, "Vision in bad weather", IEEE Conf. Computer Vision and Pattern Recognition 2000.
The Kubelka-Munk Theory for Color Image Invariant Properties - Geusebroek, Gevers.. (2002) (Correct)
No context found.
S. K. Nayar and S. G. Narasimhan. Vision in bad weather. In Proceedings of the Seventh IEEE International Conference on Computer Vision, pages 820--827. IEEE Computer Society, 1999.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC