公开(公告)号：US20140210944A1

公开(公告)日：2014-07-31

申请号：US14168403

申请日：2014-01-30

Applicant: Samsung Electronics Co., Ltd.

Inventor： Moon-Sik JEONG ,  Nipun KUMAR ,  Anshul SHARMA ,  Armin MUSTAFA ,  Karan SEHGAL ,  Kiran NANJUNDAIYER ,  Nikhil KRISHNAN ,  Revanth PAM ,  Abhijit LADE ,  Abhinandan BANNE ,  Biju NEYYAN ,  Prakash BHAGAVATHI ,  Ranjith THARAYIL

IPC: H04N13/00

CPC classification number: G06T7/55 ,  G06T2207/10016 ,  G06T2207/20092 ,  H04N13/264

Abstract: A method and apparatus are provided for converting a Two-Dimensional (2D) video to a Three-Dimensional (3D) video is disclosed. The method includes detecting a shot including similar frames in the 2D video; setting a key frame in the shot; determining whether a current frame is the key frame; when the current frame is the key frame, performing segmentation on the key frame, assigning a depth to each segmented object in the key frame; and when the current frame is not the key frame, performing the segmentation on non-key frames, and assigning the depth to each segmented object in the non-key frames.

Abstract translation: 公开了一种用于将二维（2D）视频转换成三维（3D）视频的方法和装置。 该方法包括在2D视频中检测包括类似帧的镜头; 在镜头中设置关键帧; 确定当前帧是否是关键帧; 当当前帧是关键帧时，对关键帧执行分割，为关键帧中的每个分割对象分配深度; 并且当当前帧不是关键帧时，在非关键帧上执行分割，并且在非关键帧中为每个分割对象分配深度。