Hisense Co., Ltd.

Hisense USA Corporation

Jiande Sun

Wei Liu

Lu Wang

Ju Liu

Jiangchuan Xie

The present application discloses a Three Dimensions (3D) video conversion system and method, and a key frame selection method and apparatus thereof. The key frame selection method includes: after the ith key frame is determined, calculating feature matching ratios of video frames after the ith key frame in a 2D video; selecting video frames each of which has a feature matching ratio within the range of T&#x2dc;Tas candidate key frames; selecting a video frame from the candidate key frames as the (i+1)th key frame according to re-projection errors of the candidate key frames. Since key frames are selected according to the feature matching ratios of video frames to the previous key frame, and the later key frame is selected according to the re-projection errors of the candidate key frames. Thus the selection for key frames is more reasonable, and the 2D to 3D video conversion based on more reasonable key frames may improve converted 3D video quality.

3D video conversion system and method, key frame selection method and apparatus thereof

Disclosed are a virtual viewpoint combination method and device in a multi-viewpoint video, improving the quality of the virtual viewpoint images and improving the display effects of the virtual viewpoint images under the premise of not introducing geometrical distortion. The method includes: taking two viewpoint images provided by a first camera and a second camera as reference viewpoint images, and respectively performing 3D image conversion, pinhole filling, image compensation and image convergence processing on the two viewpoint images to obtain a main virtual viewpoint image; then respectively performing depth-image processing, 3D image conversion, pinhole filling, image compensation and image convergence processing on the two viewpoint images to obtain a subordinate virtual viewpoint image; and performing filling the remaining holes in the main virtual viewpoint image on the basis of the subordinate virtual viewpoint image to obtain a final virtual viewpoint image to be combine.

Growing community of inventors

Shandong, China

Jiande Sun