Thomson Licensing

Future Wei Technologies, Inc.

Interdigital Ce Patent Holdings

Thomson Licensing Dtv

Interdigital Madison Patent Holdings

Dong-Qing Zhang

Hong Heather Yu

Izzat Hekmat Izzat

Sitaram Bhagavathy

Ana Belen Benitez

Joan Llach

James Arthur Fancher

Youngshik Yoon

Yousef Wasef Nijim

Hongbing Li

Ingo Tobias Doser

John Wus

Bo Wang

Jesus Barcons-Palau

Yong Wang

Zhenyu Wu

Yu Huang

Tao Zhang

Mike Arthur Derrenberger

Zhu Li

Shan He

Jianyu Zhang

Yifu Zhang

Miao Zhao

Ju Guo

Xueming Henry Gu

Jie Hu

Marco Antonio Vasquez

Radhakrishna Dasari

Hekmat Izzat

Qiang Hao

Qi Wang

Shu Wang

Ning Yao

Jim Arthur Fancher

Ana B Benitez

A system () and method () for combining and/or displaying text with three-dimensional (3D) content. The system () and method () inserts text at the same level as the highest depth value in the 3D content. As a result, the system () and method () of the present disclosure produces text combined with 3D content wherein the text does not obstruct the 3D effects in the 3D content and does not create visual fatigue when viewed by a viewer.

System and method for combining text with three-dimensional content

A computer program product comprising computer executable instructions stored on a non-transitory computer readable medium such that when executed by a processor, causes the processor to identify an object of interest in a visual media element, analyze the object of interest according to a defined set of rules to form a recommendation for improvement of the visual media element, and recommend the improvement to the visual media element to a user. A method comprising receiving a visual media element as an input, determining a relevant object of interest within the visual media element, analyzing an aesthetic appearance of the relevant object of interest according to a guideline, and recommending a change to the visual media element for conforming to the guideline.

Photographic picture quality improvement recommendation system using objects

A video server comprises memory to store video content obtained from multiple camera views; one or more streaming components configured to stream video content to a client application; and one or more frame feeder components. A frame feeder component is configured to access first video content corresponding to a first camera view and provide the first video content to a streaming component; access, in response to a request received at the video server to stream second video content corresponding to a second camera view, intermediate video content corresponding to one or more camera views intermediate to the first and second camera views; and access the second video content, and provide the intermediate video content and the second intermediate video to the streaming component.

Multi-view video streaming with fast and smooth view switch

A high resolution imaging system includes an imaging camera array creating a sets or frames of array images of a scene and a reference camera creating reference images of the same scene. A synchronization controller coordinates imaging of the scene by the imaging camera array and the reference camera. An image processor merges the sets of array images into high resolution images and apply a color correction to the high resolution images based on reference images. Color correction can be performed on the merged high resolution image or on individual array images prior to merger into the high resolution image.

Color corrected high resolution imaging

Methods and apparatuses for data pruning for video compression using example-based super resolution are provided. A method and apparatus for encoding is provided in which patches of video are extracted from input video, grouped together using a clustering method, and representative patches are packed into patch frames. The original video is downsized and sent either along with, or in addition to, the patch frames. At a decoder, the method and apparatus provided extract patches from the patch frames and create a patch library. The regular video frames are upsized and the low resolution patches are replaced by patches from the patch library by searching the library using the patches in the decoded regular frames as keywords. If there are no appropriate patches, no replacement is made. A post processing procedure is used to enhance the spatiotemporal smoothness of the recovered video.

Data pruning for video compression using example-based super-resolution

A system and method for combining and/or displaying text with three-dimensional content. The system and method inserts text at the same level as the highest depth value in the 3D content. One example of 3D content is a two-dimensional image and an associated depth map. In this case, the depth value of the inserted text is adjusted to match the largest depth value of the given depth map. Another example of 3D content is a plurality of two-dimensional images and associated depth maps. In this case, the depth value of the inserted text is continuously adjusted to match the largest depth value of a given depth map. A further example of 3D content is stereoscopic content having a right eye image and a left eye image. In this case the text in one of the left eye image and right eye image is shifted to match the largest depth value in the stereoscopic image. Yet another example of 3D content is stereoscopic content having a plurality of right eye images and left eye images. In this case the text in one of the left eye images or right eye images is continuously shifted to match the largest depth value in the stereoscopic images. As a result, the system and method of the present disclosure produces text combined with 3D content wherein the text does not obstruct the 3D effects in the 3D content and does not create visual fatigue when viewed by a viewer.

System and method for combining text with three dimensional content

A system and method for spatiotemporal depth extraction of images with forward and backward depth prediction are provided. The system and method of the present disclosure provide for acquiring a plurality of frames, generating a first depth map of a current frame in the plurality of frames based on a depth map of a previous frame in the plurality of frames, generating a second depth map of the current frame in the plurality of frames based on a depth map of a subsequent frame in the plurality of frames, and processing the first depth map and the second depth map to produce a third depth map for the current frame.

System and method for depth extraction of images with forward and backward depth prediction

Embodiments are provided herein to achieve video or image sequence encoding with an improved denoising algorithm that is both efficient computationally and has acceptable overhead cost in comparison to other denoising schemes for video encoding. The embodiments include using recursive bilateral filtering as part of the denoising algorithm, which is integrated into a video encoder to overcome limitations of other encoder-integrated denoising algorithms. An embodiment method includes receiving, at a filtering and residual computation function at the encoder, a macro block comprising a plurality of pixels. The filtering and residual computation function also receives, from a motion estimation function at the encoder, a reference block. The reference block comprises a plurality of reference pixels corresponding to the macro block. The filtering and residual computation function further applies a recursive bilateral filter function to each of the pixels of the macro block using the reference pixels of the reference block.

System and method for encoder-integrated media denoising

Methods and apparatus are provided for sampling-based super resolution video encoding and decoding. The encoding method receives high resolution pictures and generates low resolution pictures and metadata there from, the metadata for guiding post-decoding post-processing of the low resolution pictures and the metadata; and then encodes the low resolution pictures and the metadata using at least one encoder. The corresponding decoding method receives a bitstream and decodes low resolution pictures and metadata there from using a decoder; and then reconstructs high resolution pictures respectively corresponding to the low resolution pictures using the low resolution pictures and the metadata.

Methods and apparatus for sampling-based super resolution video encoding and decoding

An apparatus includes a patch library creator for creating a first patch library from an original version of the picture and a second patch library from a reconstructed version of the picture. Each of the libraries includes a plurality of high resolution replacement patches for replacing one or more pruned blocks during a recovery of a pruned version of the picture. A pruner generates the pruned version from the first patch library, and decides whether to respectively replace original blocks with pruned blocks responsive to a comparison between a first rate-distortion estimate and a second rate-distortion estimate. The estimates are based on both a distortion component and a bitrate component. A metadata generator generates metadata from the second patch library. The metadata is for recovering the pruned version. An encoder encodes the pruned version and the metadata.

Methods and apparatus for pruning decision optimization in example-based data pruning compression

A system and method for the color correction of an image using three-dimensional, geometrical information of the capture environment of the image includes determining geometrical properties of at least a portion of the image and modifying a look of at least the portion of the image by altering a value of at least one of the determined geometrical properties and using image formation theory. In one embodiment of the present invention, the geometrical properties of the image include at least one of light properties, surface color, reflectance properties, and scene geometry of the at least one portion of the image. In accordance with the present invention, the geometrical properties of the image are alternatively determined by using sensing devices, by inferring the geometrical properties from the image itself, or by user input.

Method and system for color correction using three-dimensional information

In accordance with an embodiment, a method of matching video content to advertising content includes electronically receiving a video content metadata from a content provider, and matching the video content metadata to advertising content metadata of a global list of advertisements. The video content metadata corresponds to video content being sent to a user device and includes at least one keyword. Furthermore, the advertising content metadata corresponds to advertising content and includes at least one keyword. Matching the video content metadata to advertising content metadata includes comparing the at least one keyword of the video content metadata to the at least one keyword of the advertising content metadata.

System and method for matching targeted advertisements for video content delivery

Methods and apparatus are provided for reducing vector quantization error through patch shifting. A method generates, from an input video sequence, one of more high resolution replacement patches, the one or more high resolution replacement patches for replacing one or more low resolution patches during a reconstruction of the input video sequence. This generating step generates the one or more high resolution replacement patches using data corresponding to a patch spatial shifting process, the patch spatial shifting process for reducing jittery artifacts caused by a motion-induced vector quantization error in the one or more high resolution replacement patches, the data for at least deriving a patch size of the one or more high resolution replacement patches such that the one or more high resolution replacement patches are generated to have the patch size greater than a patch size of the one or more low resolution patches in order to be suitable for use in the patch spatial shifting process.

Methods and apparatus for reducing vector quantization error through patch shifting

Method and apparatus for recovering a pruned version of a picture in a video sequence are disclosed. The apparatus includes a divider for dividing the pruned version of the picture into a plurality of non-overlapping blocks. The apparatus also includes a metadata decoder for decoding metadata for use in recovering the pruned version of the picture. The apparatus further includes a patch library creator for creating a patch library from a reconstructed version of the picture. The patch library includes a plurality of high resolution replacement patches for replacing the one or more pruned blocks during a recovery of the pruned version of the picture. The apparatus additionally includes a search and replacement device for performing a searching process using the metadata to find a corresponding patch for a respective one of the one or more pruned blocks from among the plurality of non-overlapping blocks and replace the respective one of the one or more pruned blocks with the corresponding patch. The signature is respectively created for each of the one or more pruned blocks, and the pruned version of the picture is recovered by comparing respective distance metrics from signatures for each of the plurality of high resolution patches to signatures for each of the one or more pruned blocks, sorting the respective distance metrics to obtain a rank list for each of the one or more pruned blocks, wherein a rank number in the rank list for a particular one of the one or more pruned blocks is used to retrieve a corresponding one of the plurality of high resolution patches in the patch library to be used to replace the particular one of the one or more pruned blocks. A patch dependency graph having a plurality of nodes and a plurality of edges is used to recover the pruned version of the picture. Each of the plurality of nodes represents a respective one of the plurality of overlapping blocks, and each of the plurality of edges represents a respective dependency of at least the respective one of the plurality of overlapping blocks.

Recovering a pruned version of a picture in a video sequence for example-based data pruning using intra-frame patch similarity

Methods and systems for a multimedia queue management solution that maintaining graceful Quality of Experience (QoE) degradation are provided. The method selects a frame from all weighted queues based on a gradient function indicating a network performance rate change and a distortion rate caused by the frame and its related frames in the queue, and dropping the selected frame and all its related frames, and continues to drop similarly chosen frame until a network performance rate change caused by the dropping frame and its related frames meets a predetermined performance metric. A frame gradient is a distortion rate divided by a network performance rate change caused by the frame and its related frames, and a distortion rate is based on a sum of each individual frame distortion rate when the frame and its related frames are replaced by some other frames derived from remaining frames based on a replacement method.

Growing community of inventors

Plainsboro, NJ, United States of America

Dong-Qing Zhang