2D to 3D Video Conversion - Revision history

Kcalagar: /* Publications */

2018-02-21T19:43:58Z

Publications

2018-02-21T19:40:28Z

Publications

2018-02-21T19:35:26Z

Publications

2016-11-09T00:00:13Z

Details

2016-11-08T23:59:23Z

Details

2016-11-08T23:58:27Z

Details

2016-11-08T23:13:34Z

Details

2016-11-08T23:13:06Z

Details

2016-11-08T23:12:18Z

Details

2016-11-08T23:09:16Z

Details

@@ Line 67: / Line 67: @@
 == Publications ==
-K. Calagari, M. Elgharib, P. Didyk, A. Kaspar, W. Matusik, and M. Hefeeda, “Gradient-based 2D-to-3D Conversion for Soccer Videos”, In Proc. of the ACM Multimedia (MM’15), p 331-340, 2015.
+K. Calagari, M. Elgharib, P. Didyk, A. Kaspar, W. Matusik, and M. Hefeeda, “Gradient-based 2D-to-3D Conversion for Soccer Videos”, In Proc. of the ACM Multimedia conference (MM’15), p 331-340, October 2015.
 K. Calagari, M. Elgharib, P. Didyk, A. Kaspar, W. Matusik, and M. Hefeeda, "Data Driven 2-D-to-3-D Video Conversion for Soccer", IEEE Transactions on Multimedia (TMM), Vol. 20, Issue 3, p 605-619, 2018

← Older revision		Revision as of 19:40, 21 February 2018
Line 69:		Line 69:
	K. Calagari, M. Elgharib, P. Didyk, A. Kaspar, W. Matusik, and M. Hefeeda, “Gradient-based 2D-to-3D Conversion for Soccer Videos”, In Proc. of the ACM Multimedia (MM’15), p 331-340, 2015.		K. Calagari, M. Elgharib, P. Didyk, A. Kaspar, W. Matusik, and M. Hefeeda, “Gradient-based 2D-to-3D Conversion for Soccer Videos”, In Proc. of the ACM Multimedia (MM’15), p 331-340, 2015.

−	K. Calagari, M. Elgharib, P. Didyk, A. Kaspar, W. Matusik, and M. Hefeeda, "Data Driven 2-D-to-3-D Video Conversion for Soccer", IEEE Transactions on Multimedia (TMM), Vol. 20, ~~No.~~3, p 605-619	+	K. Calagari, M. Elgharib, P. Didyk, A. Kaspar, W. Matusik, and M. Hefeeda, "Data Driven 2-D-to-3-D Video Conversion for Soccer", IEEE Transactions on Multimedia (TMM), Vol. 20, Issue 3, p 605-619, 2018

← Older revision		Revision as of 19:35, 21 February 2018
Line 68:		Line 68:

	K. Calagari, M. Elgharib, P. Didyk, A. Kaspar, W. Matusik, and M. Hefeeda, “Gradient-based 2D-to-3D Conversion for Soccer Videos”, In Proc. of the ACM Multimedia (MM’15), p 331-340, 2015.		K. Calagari, M. Elgharib, P. Didyk, A. Kaspar, W. Matusik, and M. Hefeeda, “Gradient-based 2D-to-3D Conversion for Soccer Videos”, In Proc. of the ACM Multimedia (MM’15), p 331-340, 2015.
		+
		+	K. Calagari, M. Elgharib, P. Didyk, A. Kaspar, W. Matusik, and M. Hefeeda, "Data Driven 2-D-to-3-D Video Conversion for Soccer", IEEE Transactions on Multimedia (TMM), Vol. 20, No.3, p 605-619

@@ Line 26: / Line 26: @@
 * ''' Visual Search: ''' For each frame of the query video we identify the K most similar frames to it based on GIST and color.
-* ''' Block-based Matching:  ''' Using the K candidate frames we construct a matching image which is similar to the query frame and provides a mapping between the candidates and the query frame. To construct this matching image, we divide the query frame into small blocks and compare each block against all possible blocks in the K candidate images. The block with the smallest Euclidean distance is chosen as the corresponding block.
+* ''' Block-based Matching:  ''' Using the K candidate frames we construct a matching image which is similar to the query frame and provides a mapping between the candidates and the query frame. To construct this matching image, we divide the query frame into small blocks and compare each block against all possible blocks in the K candidates. The block with the smallest Euclidean distance is chosen as the corresponding block.
 * ''' Poisson Reconstruction:  ''' We copy the corresponding depth gradients from the matched image to the query frame and reconstruct the depth values from the copied depth gradients using the Poisson equation.

@@ Line 26: / Line 26: @@
 * ''' Visual Search: ''' For each frame of the query video we identify the K most similar frames to it based on GIST and color.
-* ''' Block-based Matching:  ''' Using the K candidate images we construct a matching image which is similar to the query frame and provides a mapping between the candidates and the query frame. To construct this matching image, we divide the query frame into small blocks and compare each block against all possible blocks in the K candidate images. The block with the smallest Euclidean distance is chosen as the corresponding block.
+* ''' Block-based Matching:  ''' Using the K candidate frames we construct a matching image which is similar to the query frame and provides a mapping between the candidates and the query frame. To construct this matching image, we divide the query frame into small blocks and compare each block against all possible blocks in the K candidate images. The block with the smallest Euclidean distance is chosen as the corresponding block.
 * ''' Poisson Reconstruction:  ''' We copy the corresponding depth gradients from the matched image to the query frame and reconstruct the depth values from the copied depth gradients using the Poisson equation.

← Older revision		Revision as of 23:58, 8 November 2016
Line 22:		Line 22:


−	The main components of of our depth gradient based conversion technique as ~~shown in the following figure are~~:	+	The main components of of our depth gradient based conversion technique are as follows:

	* ''' Visual Search: ''' For each frame of the query video we identify the K most similar frames to it based on GIST and color.		* ''' Visual Search: ''' For each frame of the query video we identify the K most similar frames to it based on GIST and color.

← Older revision		Revision as of 23:13, 8 November 2016
Line 29:		Line 29:

	* ''' Poisson Reconstruction: ''' We copy the corresponding depth gradients from the matched image to the query frame and reconstruct the depth values from the copied depth gradients using the Poisson equation.		* ''' Poisson Reconstruction: ''' We copy the corresponding depth gradients from the matched image to the query frame and reconstruct the depth values from the copied depth gradients using the Poisson equation.
−

	* ''' Object Boundary Cuts: ''' In order to maintain sharp and accurate object boundaries, we create object masks, detect their edges through Canny edge detector, and disconnect pixels from the object boundaries by not allowing them to use an object boundary pixel as a valid neighbor.		* ''' Object Boundary Cuts: ''' In order to maintain sharp and accurate object boundaries, we create object masks, detect their edges through Canny edge detector, and disconnect pixels from the object boundaries by not allowing them to use an object boundary pixel as a valid neighbor.