-
公开(公告)号:US09167232B2
公开(公告)日:2015-10-20
申请号:US13543179
申请日:2012-07-06
申请人: Wen-Nung Lie , Hsiang-Yun Huang , Wei-Chih Chen
发明人: Wen-Nung Lie , Hsiang-Yun Huang , Wei-Chih Chen
CPC分类号: H04N13/264 , G06K9/00765 , G06T7/579 , G06T2207/10016 , G06T2207/10024 , G06T2207/20021
摘要: A 2D video to 3D video conversion system includes a video content analysis unit, a depth estimation unit, a post-processing unit, and a stereoscopic video generation unit. The video content analysis unit can analyze a 2D video datum and extract useful information including motion and color from the 2D video datum for depth estimation. The depth estimation unit is adapted for receiving the useful information, calculating motion cue and contrast cue for initial depth estimation, and generating an initial depth map. The post-processing unit is adapted for correcting the initial depth map in spatial domain and temporal domain to increase accuracy in spatial domain and depth continuity between adjacent time instances and for processing the caption in the video to generate a final depth map. The stereoscopic video generation unit is adapted for synthesizing 3D video datum from the final depth map and 2D video datum.
摘要翻译: 2D视频到3D视频转换系统包括视频内容分析单元,深度估计单元,后处理单元和立体视频生成单元。 视频内容分析单元可以分析2D视频数据,并从2D视频数据中提取包括运动和颜色的有用信息以进行深度估计。 深度估计单元适于接收有用信息,计算用于初始深度估计的运动提示和对比度提示,以及生成初始深度图。 后处理单元适于在空间域和时域中校正初始深度图,以增加相邻时间实例之间的空间域精度和深度连续性,并用于处理视频中的字幕以生成最终深度图。 立体视频生成单元适于从最终深度图和2D视频数据合成3D视频数据。
-
公开(公告)号:US20100036644A1
公开(公告)日:2010-02-11
申请号:US12188192
申请日:2008-08-07
申请人: Yu-Shiang Yang , Te-Hung Wu , Yung-Feng Cheng , Chuen Huei Yang , Hsiang-Yun Huang , Hui-Fang Kuo , Shih-Ming Kuo , Lun-Hung Chen
发明人: Yu-Shiang Yang , Te-Hung Wu , Yung-Feng Cheng , Chuen Huei Yang , Hsiang-Yun Huang , Hui-Fang Kuo , Shih-Ming Kuo , Lun-Hung Chen
IPC分类号: G06F17/50
CPC分类号: G06F17/5068 , G06F2217/12 , Y02P90/265
摘要: A method to selectively amend a layout pattern is disclosed. First, a layout pattern including at least a first group and a second group is provided, wherein each one of the first group and the second group respectively includes multiple members. Second, a simulation procedure and an amendment procedure are respectively performed on all the members of the first group and the second group to obtain an amended first group and an amended second group. Then, the amended first group and the amended second group are verified as being on target or not. Afterwards, the layout pattern including the on target amended first group and the on target amended second group is output.
摘要翻译: 公开了一种选择性地修改布局图案的方法。 首先,提供包括至少第一组和第二组的布局图案,其中第一组和第二组中的每一个分别包括多个构件。 其次,分别对第一组和第二组的所有成员进行模拟程序和修改程序,以获得修改后的第一组和第二组。 然后,经修改的第一组和第二组被修正为目标。 之后,输出了包括目标修正的第一组和目标修正的第二组的布局模式。
-
公开(公告)号:US20130162768A1
公开(公告)日:2013-06-27
申请号:US13543179
申请日:2012-07-06
申请人: Wen-Nung LIE , Hsiang-Yun Huang , Wei-Chih Chen
发明人: Wen-Nung LIE , Hsiang-Yun Huang , Wei-Chih Chen
IPC分类号: H04N13/00
CPC分类号: H04N13/264 , G06K9/00765 , G06T7/579 , G06T2207/10016 , G06T2207/10024 , G06T2207/20021
摘要: A 2D video to 3D video conversion system includes a video content analysis unit, a depth estimation unit, a post-processing unit, and a stereoscopic video generation unit. The video content analysis unit can analyze a 2D video datum and extract useful information including motion and color from the 2D video datum for depth estimation. The depth estimation unit is adapted for receiving the useful information, calculating motion cue and contrast cue for initial depth estimation, and generating an initial depth map. The post-processing unit is adapted for correcting the initial depth map in spatial domain and temporal domain to increase accuracy in spatial domain and depth continuity between adjacent time instances and for processing the caption in the video to generate a final depth map. The stereoscopic video generation unit is adapted for synthesizing 3D video datum from the final depth map and 2D video datum.
摘要翻译: 2D视频到3D视频转换系统包括视频内容分析单元,深度估计单元,后处理单元和立体视频生成单元。 视频内容分析单元可以分析2D视频数据,并从2D视频数据中提取包括运动和颜色的有用信息以进行深度估计。 深度估计单元适于接收有用信息,计算用于初始深度估计的运动提示和对比度提示,以及生成初始深度图。 后处理单元适于在空间域和时域中校正初始深度图,以增加相邻时间实例之间的空间域精度和深度连续性,并用于处理视频中的字幕以生成最终深度图。 立体视频生成单元适于从最终深度图和2D视频数据合成3D视频数据。
-
公开(公告)号:US08042069B2
公开(公告)日:2011-10-18
申请号:US12188192
申请日:2008-08-07
申请人: Yu-Shiang Yang , Te-Hung Wu , Yung-Feng Cheng , Chuen Huei Yang , Hsiang-Yun Huang , Hui-Fang Kuo , Shih-Ming Kuo , Lun-Hung Chen
发明人: Yu-Shiang Yang , Te-Hung Wu , Yung-Feng Cheng , Chuen Huei Yang , Hsiang-Yun Huang , Hui-Fang Kuo , Shih-Ming Kuo , Lun-Hung Chen
IPC分类号: G06F17/50
CPC分类号: G06F17/5068 , G06F2217/12 , Y02P90/265
摘要: A method to selectively amend a layout pattern is disclosed. First, a layout pattern including at least a first group and a second group is provided, wherein each one of the first group and the second group respectively includes multiple members. Second, a simulation procedure and an amendment procedure are respectively performed on all the members of the first group and the second group to obtain an amended first group and an amended second group. Then, the amended first group and the amended second group are verified as being on target or not. Afterwards, the layout pattern including the on target amended first group and the on target amended second group is output.
摘要翻译: 公开了一种选择性地修改布局图案的方法。 首先,提供包括至少第一组和第二组的布局图案,其中第一组和第二组中的每一个分别包括多个构件。 其次,分别对第一组和第二组的所有成员进行模拟程序和修改程序,以获得修改后的第一组和第二组。 然后,经修改的第一组和第二组被修正为目标。 之后,输出了包括目标修正的第一组和目标修正的第二组的布局模式。
-
-
-