公开(公告)号：US20240214651A1

公开(公告)日：2024-06-27

申请号：US18288344

申请日：2021-05-11

申请人： NOVI DIGITAL ENTERTAINMENT PRIVATE LIMITED

发明人： Shenglong Lyu ,  Jian Hui ,  Lu Zhang ,  Deming Lu ,  Tao Xiong

IPC分类号： H04N21/8549 ,  G06T13/40 ,  G06T13/80 ,  H04N21/84 ,  H04N21/8545

CPC分类号： H04N21/8549 ,  G06T13/40 ,  G06T13/80 ,  H04N21/84 ,  H04N21/8545 ,  G06T2210/61

摘要： A method and system (150) for generating smart thumbnails is disclosed. The method includes receiving a thumbnail and metadata in relation to a content stored in a content store (152). The metadata is analyzed to identify a key content element of the content. If the key content element is present in the thumbnail, one or more features related to the key content element are extracted and caused to be animated to create an animated content element. One or more textual snippets are generated based on the metadata, and a textual snippet is converted into a speech form to configure an audio version of the textual snippet. The audio version is combined with the animated content element to create a speaking content element. The speaking content element is embedded in place of the key content element in the thumbnail to generate the smart thumbnail.

公开(公告)号：US20230421851A1

公开(公告)日：2023-12-28

申请号：US18339942

申请日：2023-06-22

申请人： Novi Digital Entertainment Private Limited

发明人： Youqiang Zhang ,  Tao Xiong

IPC分类号： H04N21/462 ,  H04N21/44 ,  H04N21/472

CPC分类号： H04N21/4621 ,  H04N21/44008 ,  H04N21/472

摘要： A system and method for enhancing video resolution is disclosed. A Low-Resolution (LR) video including a plurality of LR images is received. The LR video is converted to a High-Resolution (HR) video by transforming at least one LR image to a HR image. Pixel unshuffle is performed to rearrange image portions in the LR image to generate a set of downsampled sub-images. Further, shallow features are extracted from the set of downsampled sub-image. The shallow features extracted corresponding to the set of downsampled sub-images configure a feature space. The shallow features are processed using a series of inverted residual blocks to generate enhanced features corresponding to the set of downsampled sub-images. The enhanced features are mapped to a high resolution feature space using pixel shuffle to generate the HR image corresponding to the LR image.