Abstract:
This paper extends the traditional binocular stereo problem into the spacetime domain, in which a pair of video streams is matched simultaneously instead of matching pairs of images frame by frame. Almost any existing stereo algorithm may be extended in this manner simply by replacing the image matching term with a spacetime term. By utilizing both spatial and temporal appearance variation, this modification reduces ambiguity and increases accuracy. Three major applications for spacetime stereo are proposed in this paper. First, spacetime stereo serves as a general framework for structured light scanning and generates high quality depth maps for static scenes. Second, spacetime stereo is effective for a class of natural scenes, such as waving trees and flowing water, which have repetitive textures and chaotic behaviors and are challenging for existing stereo algorithms. Third, the approach is one of very few existing methods that can robustly reconstruct objects that are moving and deforming over time, achieved by use of oriented spacetime windows in the matching procedure. Promising experimental results in the above three scenarios are demonstrated. 1.
Citations
|
365
|
A taxonomy and evaluation of dense two-frame stereo correspondence algorithms
– Scharstein, Szeliski
- 2002
|
|
195
|
A stereo matching algorithm with an adaptive window: Theory and experiment
– Kanade, Okutomi
- 1994
|
|
136
|
Lucas-Kanade 20 Years On: A Unifying Framework
– Baker, Matthews
- 2002
|
|
129
|
Multi-camera scene reconstruction via graph cuts
– Kolmogorov, Zabih
- 2002
|
|
72
|
Camera calibration toolbox for Matlab, http://www.vision.caltech.edu/bouguetj/calib doc
– Bouguet
|
|
61
|
Three-dimensional scene flow
– Vedula, Baker, et al.
- 1999
|
|
46
|
3D photography on your desk
– Bouguet, Perona
- 1998
|
|
38
|
Stripe boundary codes for real-time structured-light range scanning of moving objects
– Hall-Holt, Rusinkiewicz
|
|
36
|
Better Optical Triangulation through Spacetime Analysis
– Curless, Levoy
- 1995
|
|
36
|
Rapid Shape Acquisition Using Color Structured Light and
– Zhang, Curless, et al.
- 2002
|
|
34
|
Spacetime stereo: A unifying framework for depth from triangulation
– Davis, Ramamoorthi, et al.
- 2003
|
|
28
|
Range-imaging system utilizing nematic liquid crystal mask
– Sato, Inokuchi
- 1987
|
|
16
|
A very fast vlsi rangefinder
– Kanade, Gruss, et al.
- 1991
|
|
16
|
Integrated 3d scene flow and structure recovery from multiview image sequences
– Zhang, Kambhamettu
- 2000
|
|
13
|
Acquisition and visualization of colored 3D objects
– Pulli, Abi-Rached, et al.
- 1998
|
|
8
|
On 3D scene flow and structure estimation
– Zhang, Kambhamettu
|
|
7
|
Motion-stereo integration for depth estimation
– Strecha, Gool
- 2002
|
|
6
|
A step towards sequence to sequence alignment
– Caspi, Irani
- 2000
|
|
5
|
Dynamic depth recovery from multiple synchronized video streams
– Tao, Sawhney, et al.
- 2001
|
|
3
|
Scene capture by surfel sampling: from multi-view streams to non-rigid 3D motion, shape and reflectance
– Carceroni, Kutulakos
- 2001
|
|
2
|
Correlation based estimatin of ego-motion and structure from motion and stereo
– Mandelbaum, Salgian, et al.
- 1999
|
