Immersive Content Generation from Standard 2D Videos - Revision history

Mhefeeda at 17:28, 6 August 2021

2021-08-06T17:28:08Z

Mhefeeda: /* Abstract */

2021-08-06T17:24:45Z

Abstract

Kcalagar: /* Publications */

2018-02-21T19:43:48Z

Publications

Kcalagar: /* Publications */

2018-02-21T19:41:48Z

Publications

Kcalagar: /* Details */

2017-09-15T22:04:24Z

Details

Kcalagar: /* Details */

2017-09-15T22:03:11Z

Details

Kcalagar: /* Details */

2017-09-15T22:01:14Z

Details

Kcalagar: /* Details */

2017-09-15T22:00:05Z

Details

Kcalagar: /* Details */

2017-09-15T21:55:50Z

Details

Kcalagar: /* Details */

2017-09-15T21:54:14Z

Details

@@ Line 5: / Line 5: @@
 == Abstract ==
-The aim of this project is to create compelling immersive videos suitable for VR (virtual reality) devices using only standard 2D videos. The focus of the work is on field sports such as soccer, hockey, basketball, etc. Currently the only way to create immersive content is by using multiple cameras and 360 camera rigs. This means that in addition to the already existing standard 2D cameras around the field, an expensive infrastructure should be added and managed in order to shoot and generate immersive content. In this project, however, we propose a more favorable alternative in which we can utilize the content of the already existing standard 2D cameras around the field to generate an immersive video.
+The aim of this project is to create compelling immersive videos suitable for VR (virtual reality) devices using only standard 2D videos. The focus of the work is on field sports such as soccer, hockey, basketball, etc. Currently, the only way to create immersive content is by using multiple cameras and 360 camera rigs. This means that in addition to the already existing standard 2D cameras around the field, an expensive infrastructure should be added and managed in order to shoot and generate immersive content. In this project, however, we propose a more favorable alternative in which we can utilize the content of the already existing standard 2D cameras around the field to generate an immersive video.
 <center>
@@ Line 33: / Line 33: @@
 * '''Removing parallax between all video feeds:''' In a regular sports production the cameras are usually placed meters away from each other, causing a huge amount of parallax between them. By estimating the 3D pixel positions and the relative camera parameters, we warp each video feed to the position of the main camera to remove such parallax.
 * '''Overlaying frames on the panorama:''' To seamlessly blend the copied parts with the background, we use Poisson blending. For each frame, we first overlay the main feed. Players missing from the main feed are then identified and copied from the left and right video feeds.
 <center>
@@ Line 44: / Line 45: @@
 The following figure shows examples of final panoramas generated by our technique. The blue arrows indicate the missing players that were copied from the left and right feeds.
 <center>
@@ Line 57: / Line 59: @@
 ==  Publications ==
-K. Calagari, M. Elgharib, S. Shirmohammadi, and M. Hefeeda, “Sports VR Content Generation from Regular Camera Feeds”, In Proc. of the ACM Multimedia conference (MM’17), p 699-707, October 2017.
+K. Calagari, M. Elgharib, S. Shirmohammadi, and M. Hefeeda, “[https://www2.cs.sfu.ca/~mhefeeda/Papers/mm17_2d-vr.pdf|Sports VR Content Generation from Regular Camera Feeds]”, In Proc. of the ACM Multimedia conference (MM’17), p 699-707, October 2017.

@@ Line 9: / Line 9: @@
 <center>
 {| border="0"
-|[[Image:field.png|center|The aim is to create compelling immersive videos using only standard 2D videos.|500px]]
+|[[Image:field.png|center|The aim is to create compelling immersive videos using only standard 2D videos.|500px-field]]
 |-
 |align="center" width="500pt"|The aim is to create compelling immersive videos using only standard 2D videos.

← Older revision		Revision as of 19:43, 21 February 2018
Line 57:		Line 57:
	== Publications ==		== Publications ==

−	K. Calagari, M. Elgharib, S. Shirmohammadi, and M. Hefeeda, “Sports VR Content Generation from Regular Camera Feeds”, In Proc. of the ACM Multimedia (MM’17), p 699-707, October 2017.	+	K. Calagari, M. Elgharib, S. Shirmohammadi, and M. Hefeeda, “Sports VR Content Generation from Regular Camera Feeds”, In Proc. of the ACM Multimedia conference (MM’17), p 699-707, October 2017.

← Older revision		Revision as of 19:41, 21 February 2018
Line 57:		Line 57:
	== Publications ==		== Publications ==

−	K. Calagari, M. Elgharib, S. Shirmohammadi, and M. Hefeeda, “Sports VR Content Generation from Regular Camera Feeds”, In Proc. of the ACM Multimedia (MM’17), 2017.	+	K. Calagari, M. Elgharib, S. Shirmohammadi, and M. Hefeeda, “Sports VR Content Generation from Regular Camera Feeds”, In Proc. of the ACM Multimedia (MM’17), p 699-707, October 2017.

@@ Line 30: / Line 30: @@
 The main steps for generating an immersive video from 2D cameras around the field can be described as follows:
-* Generating a still panorama using the motion of the main camera:, The viewing angle in regular sports videos is usually not wide enough for an immersive experience. In order to improve the sense of presence, a wider viewing angle is needed. As a result,we increase the viewing angle by utilizing the camera rotation, and generating a panorama image which includes the static parts of the scene. The camera rotation is transformed to a wider viewing angle by aligning the frames using image registration techniques, and applying median filtering.
+* '''Generating a still panorama using the motion of the main camera:''' The viewing angle in regular sports videos is usually not wide enough for an immersive experience. In order to improve the sense of presence, a wider viewing angle is needed. As a result,we increase the viewing angle by utilizing the camera rotation, and generating a panorama image which includes the static parts of the scene. The camera rotation is transformed to a wider viewing angle by aligning the frames using image registration techniques, and applying median filtering.
-* Removing parallax between all video feeds:, In a regular sports production the cameras are usually placed meters away from each other, causing a huge amount of parallax between them. By estimating the 3D pixel positions and the relative camera parameters, we warp each video feed to the position of the main camera to remove such parallax.
+* '''Removing parallax between all video feeds:''' In a regular sports production the cameras are usually placed meters away from each other, causing a huge amount of parallax between them. By estimating the 3D pixel positions and the relative camera parameters, we warp each video feed to the position of the main camera to remove such parallax.
-* Overlaying frames on the panorama:, To seamlessly blend the copied parts with the background, we use Poisson blending. For each frame, we first overlay the main feed. Players missing from the main feed are then identified and copied from the left and right video feeds.
+* '''Overlaying frames on the panorama:''' To seamlessly blend the copied parts with the background, we use Poisson blending. For each frame, we first overlay the main feed. Players missing from the main feed are then identified and copied from the left and right video feeds.
 <center>

@@ Line 31: / Line 31: @@
 # Generating a still panorama using the motion of the main camera: The viewing angle in regular sports videos is usually not wide enough for an immersive experience. In order to improve the sense of presence, a wider viewing angle is needed. As a result,we increase the viewing angle by utilizing the camera rotation, and generating a panorama image which includes the static parts of the scene. The camera rotation is transformed to a wider viewing angle by aligning the frames using image registration techniques, and applying median filtering.
 # Removing parallax between all video feeds: In a regular sports production the cameras are usually placed meters away from each other, causing a huge amount of parallax between them. By estimating the 3D pixel positions and the relative camera parameters, we warp each video feed to the position of the main camera to remove such parallax.
 # Overlaying frames on the panorama: To seamlessly blend the copied parts with the background, we use Poisson blending. For each frame, we first overlay the main feed. Players missing from the main feed are then identified and copied from the left and right video feeds.

← Older revision		Revision as of 21:54, 15 September 2017
Line 55:		Line 55:
	\|}		\|}
	</center>		</center>
		+
		+	== Publications ==
		+
		+	K. Calagari, M. Elgharib, S. Shirmohammadi, and M. Hefeeda, “Sports VR Content Generation from Regular Camera Feeds”, In Proc. of the ACM Multimedia (MM’17), 2017.