Abstract:
Reflections exist in many natural images. For example, shiny surfaces attempt to reflect the surrounding scene, thus, resulting in a composite image that contains the mixture of reflected light and transmitted light. When viewed from a moving camera, different components appear to move differently relative to each other. Although multiple motion recovery problem has been previously studied by many researchers, few algorithms have been proposed to recover the component images themselves. In this paper, we present a novel approach to accurately separate the individual image components from a sequence of composite images. The separation of the images is realized in the Fourier domain, where each image component is represented by its frequency elements. A minimization framework exploring the magnitude and phase constraints between each frequency element is devised to find the correct motion vectors and decouple the composite frequency elements into individual components. Experimental results using both synthetic and real images demonstrate the efficiency and robustness of our algorithm. 1
Citations
|
120
|
Smoothness in layers: Motion segmentation using nonparametric mixture estimation
– Weiss
- 1997
|
|
102
|
A threeframe algorithm for estimating two-component image motion
– Bergen, Burt, et al.
- 1992
|
|
70
|
A layered approach to stereo reconstruction
– Baker, Szeliski, et al.
- 1998
|
|
44
|
Layer extraction from multiple images containing reflections and transparency
– Szeliski, Avidan, et al.
- 2000
|
|
39
|
Separation of reflection components using color and polarization
– Nayar, Fang, et al.
- 1997
|
|
29
|
Using color to separate reflection components. COLOR research and applications
– Shafer
- 1985
|
|
22
|
Separation of transparent layers using focus
– SCHECHNER, KIRYATI, et al.
- 2000
|
|
19
|
Polarization-based decorrelation of transparent layers: The inclination angle of an invisible surface
– Schechner, Shamir, et al.
- 1999
|
|
12
|
Decoupling Fourier components of dynamic image sequences: a theory of signal separation, image segmentation and optical flow estimation
– Vernon
- 1998
|
|
12
|
Separating reflections and lighting using independent components analysis
– Farid, Adelson
- 1999
|
|
10
|
Separating real and virtual objects from their overlapping images
– Ohnishi, Kumaki, et al.
- 1996
|
|
6
|
Blind recovery of transparent and semireflected scenes
– Schechner, Kiryati, et al.
- 2000
|
|
6
|
Separation of diffuse and specular reflection in color images
– Lin, Shum
- 2001
|
|
3
|
Fourier Vision–Segmentation and Velocity Measurement Using the Fourier Transform
– Vernon
- 2001
|
|
3
|
Layered representation from motion analysis
– Wang, Adelson
- 1993
|
|
1
|
Segmentation in dynamic image sequences by isolation of coherent wave profiles
– Vernon
|
