A Data-Driven Regularization Model for Stereo and Flow
Data-driven techniques can reliably build semantic correspondence among images. In this paper, we present a new regularization model for stereo or flow through transferring the shape information of the disparity or flow from semantically matched patches in the training database. Compared to previous...
Main Authors: | Freeman, William T. (Contributor), Wei, Donglai (Contributor), Liu, Ce (Author) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor) |
Format: | Article |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers (IEEE),
2015-12-15T02:48:28Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Summary study of data-driven photometric stereo methods
by: Qian Zheng, et al.
Published: (2020-06-01) -
Data-Driven Regularization Parameter Selection in Dynamic MRI
by: Matti Hanhela, et al.
Published: (2021-02-01) -
Effective Data-Driven Calibration for a Galvanometric Laser Scanning System Using Binocular Stereo Vision
by: Junchao Tu, et al.
Published: (2018-01-01) -
The visual perception of 3D shape from stereo: Metric structure or regularization constraints?
by: Yu, Ying
Published: (2017) -
Analysis and measure of novel stereo-garage driven by linear induction motor
by: Lu Qinfen, et al.
Published: (2015-12-01)