PATENTS
High quality 2D to 3D conversion:
ABSTRACT
A method for converting a two-dimensional (2D) video to a three-dimensional (3D) video is disclosed. The method provides a User Interface (UI) to detect shot boundary in shots and select a key frame. Then the method checks whether the current frame is a key frame that has to be segmented from among at least one 2D video frame of a 2D video. The key frame is segmented by separating at least one object in the key frame and storing information about the segmentation. The segmented 2D frames are generated by segmenting at least one 2D video frame except the key frame in the same manner as the key frame is segmented, based on the stored segmentation information. Then the user assigns depth to at least one object in the key frame and propagates the depth to non-segmented non-key frames. Finally, the method stores the frames as 3D video.
(India 403/CHE/2013)
A method for converting a two-dimensional (2D) video to a three-dimensional (3D) video is disclosed. The method provides a User Interface (UI) to detect shot boundary in shots and select a key frame. Then the method checks whether the current frame is a key frame that has to be segmented from among at least one 2D video frame of a 2D video. The key frame is segmented by separating at least one object in the key frame and storing information about the segmentation. The segmented 2D frames are generated by segmenting at least one 2D video frame except the key frame in the same manner as the key frame is segmented, based on the stored segmentation information. Then the user assigns depth to at least one object in the key frame and propagates the depth to non-segmented non-key frames. Finally, the method stores the frames as 3D video.
(India 403/CHE/2013)









