公开(公告)号：WO2016186925A1

公开(公告)日：2016-11-24

申请号：PCT/US2016/031871

申请日：2016-05-11

Applicant: TMM, INC.

Inventor： TAI, Angelia ,  KERR, David ,  BERNIBER, Nicolas ,  LEE, Vitus

IPC: H04N21/2662 ,  H04N21/258

CPC classification number: H04N21/234363

Abstract: Disclosed is a method of performing upscaling that includes the steps of: parsing an input video; breaking the input video into individual frames; performing upscaling on the individual frames to produce upscaled frames; and stitching the upscaled frames together to produce an upscaled video.

Abstract translation: 公开了一种执行升频的方法，包括以下步骤：解析输入视频; 将输入视频分解成单个帧; 在单个帧上执行升级以产生放大的帧; 并将放大的帧拼接在一起以产生放大的视频。

公开(公告)号：WO2016186927A1

公开(公告)日：2016-11-24

申请号：PCT/US2016/031877

申请日：2016-05-11

Applicant: TMM, INC.

Inventor： ZHOU, Da Qing ,  BERNIER, Nicolas ,  KERR, David

IPC: G06T3/40 ,  H04N19/132

CPC classification number: H04N21/234363 ,  G06T3/4053 ,  H04N19/132 ,  H04N21/231 ,  H04N21/233

Abstract: In one aspect, the invention relates to a method of performing upsampling, that includes the steps of: receiving an input image; generating an initial upsampled image using the input image; generating a low-passed image using the input image; and performing self-similarity upsampling using the upsampled image and the low- passed image.

Abstract translation: 一方面，本发明涉及一种执行上采样的方法，包括以下步骤：接收输入图像; 使用所述输入图像生成初始上采样图像; 使用输入图像生成低通图像; 以及使用上采样图像和低通图像执行自相似性上采样。

公开(公告)号：WO2016186925A8

公开(公告)日：2016-11-24

申请号：PCT/US2016/031871

申请日：2016-05-11

Applicant: TMM, INC.

Inventor： TAI, Angelia ,  KERR, David ,  BERNIER, Nicolas ,  LEE, Vitus

IPC: H04N21/2662 ,  H04N21/258

Abstract: Disclosed is a method of performing upscaling that includes the steps of: parsing an input video; breaking the input video into individual frames; performing upscaling on the individual frames to produce upscaled frames; and stitching the upscaled frames together to produce an upscaled video.

Abstract translation: 公开了一种执行放大的方法，其包括以下步骤：解析输入视频; 将输入的视频分成单独的帧; 对各个帧执行放大以产生放大的帧; 并将放大的帧拼接在一起以产生放大的视频。

公开(公告)号：WO2016040939A1

公开(公告)日：2016-03-17

申请号：PCT/US2015/049970

申请日：2015-09-14

Applicant: TMM, INC.

Inventor： LEE, Vitus ,  KERR, David ,  ZIMMERMAN, Oliver

IPC: H04N19/124 ,  H04N19/50 ,  G06F3/048

CPC classification number: G06F3/0486 ,  G06F3/0481 ,  G06F3/04842 ,  G06F17/3079 ,  G06T7/246 ,  H04N19/124 ,  H04N19/162 ,  H04N19/167 ,  H04N19/17 ,  H04N19/20

Abstract: Examples of the present disclosure relate to performing subject oriented compression. A content file, such as a video file, may be received. One or more subjects of interest may be identified in the content file. The identified subjects of interest may be associated with a quantization value that is less than a quantization value associated with the rest of the content. When the content is compressed/encoded, the subjects of interest are compressed/encoded using their associated quantization value while the rest of the content is compressed/encoded using a larger quantization value.

Abstract translation: 本公开的示例涉及执行面向对象的压缩。 可以接收诸如视频文件的内容文件。 可以在内容文件中识别感兴趣的一个或多个主题。 所识别的感兴趣对象可以与小于与其余内容相关联的量化值的量化值相关联。 当内容被压缩/编码时，利用它们相关联的量化值对感兴趣的对象进行压缩/编码，而剩余的内容使用更大的量化值进行压缩/编码。