公开(公告)号：US20240080444A1

公开(公告)日：2024-03-07

申请号：US18507279

申请日：2023-11-13

Applicant: GOOGLE LLC

Inventor： Di Chen ,  Sam John

IPC: H04N19/119 ,  H04N19/146 ,  H04N19/159

CPC classification number: H04N19/119 ,  H04N19/146 ,  H04N19/159

Abstract: Bitrate-adaptive segmentation is performed for transcoding a video stream uploaded to an online video platform for hosting and later playback to platform users. The video stream is segmented into chunks based on prediction-based bit costs determined for frames of the video stream rather than based on scene changes detected within the video stream. The bitrate-adaptive segmentation includes determining inter-prediction bit costs and intra-prediction bit costs for frames of the video stream based on information indicated within a pass log based on a first pass encoding of the video stream, determining chunk boundaries for segmenting the video stream into a chunk based on the inter-prediction bit costs and the intra-prediction bit costs for the frames, and transcoding the chunk to produce a transcoded video stream.

公开(公告)号：US20230101806A1

公开(公告)日：2023-03-30

申请号：US17908352

申请日：2020-05-19

Applicant: Google LLC

Inventor： Sam John ,  Balineedu Adsumilli ,  Akshay Gadde

IPC: H04N19/40 ,  H04N19/184 ,  H04N19/119 ,  H04N19/192 ,  H04N19/147

Abstract: A learning model is trained for rate-distortion behavior prediction against a corpus of a video hosting platform and used to determine optimal bitrate allocations for video data given video content complexity across the corpus of the video hosting platform. Complexity features of the video data are processed using the learning model to determine a rate-distortion cluster prediction for the video data, and transcoding parameters for transcoding the video data are selected based on that prediction. The rate-distortion clusters are modeled during the training of the learning model, such as based on rate-distortion curves of video data of the corpus of the video hosting platform and based on classifications of such video data. This approach minimizes total corpus egress and/or storage while further maintaining uniformity in the delivered quality of videos by the video hosting platform.

公开(公告)号：US20230300330A1

公开(公告)日：2023-09-21

申请号：US17696760

申请日：2022-03-16

Applicant: GOOGLE LLC

Inventor： Di Chen ,  Sam John

IPC: H04N19/119 ,  H04N19/159 ,  H04N19/146

CPC classification number: H04N19/119 ,  H04N19/159 ,  H04N19/146

Abstract: Bitrate-adaptive segmentation is performed for transcoding a video stream uploaded to an online video platform for hosting and later playback to platform users. The video stream is segmented into chunks based on prediction-based bit costs determined for frames of the video stream rather than based on scene changes detected within the video stream. The bitrate-adaptive segmentation includes determining inter-prediction bit costs and intra-prediction bit costs for frames of the video stream based on information indicated within a pass log based on a first pass encoding of the video stream, determining chunk boundaries for segmenting the video stream into a chunk based on the inter-prediction bit costs and the intra-prediction bit costs for the frames, and transcoding the chunk to produce a transcoded video stream.

公开(公告)号：US20240187618A1

公开(公告)日：2024-06-06

申请号：US18440013

申请日：2024-02-13

Applicant: GOOGLE LLC

Inventor： Sam John ,  Balineedu Adsumilli ,  Akshay Gadde

IPC: H04N19/40 ,  H04N19/119 ,  H04N19/147 ,  H04N19/184 ,  H04N19/192

CPC classification number: H04N19/40 ,  H04N19/119 ,  H04N19/147 ,  H04N19/184 ,  H04N19/192

Abstract: A learning model is trained for rate-distortion behavior prediction against a corpus of a video hosting platform and used to determine optimal bitrate allocations for video data given video content complexity across the corpus of the video hosting platform. Complexity features of the video data are processed using the learning model to determine a rate-distortion cluster prediction for the video data, and transcoding parameters for transcoding the video data are selected based on that prediction. The rate-distortion clusters are modeled during the training of the learning model, such as based on rate-distortion curves of video data of the corpus of the video hosting platform and based on classifications of such video data. This approach minimizes total corpus egress and/or storage while further maintaining uniformity in the delivered quality of videos by the video hosting platform.

公开(公告)号：US11924449B2

公开(公告)日：2024-03-05

申请号：US17908352

申请日：2020-05-19

Applicant: Google LLC

Inventor： Sam John ,  Balineedu Adsumilli ,  Akshay Gadde

IPC: H04N19/40 ,  H04N19/119 ,  H04N19/147 ,  H04N19/184 ,  H04N19/192

CPC classification number: H04N19/40 ,  H04N19/119 ,  H04N19/147 ,  H04N19/184 ,  H04N19/192

Abstract: A learning model is trained for rate-distortion behavior prediction against a corpus of a video hosting platform and used to determine optimal bitrate allocations for video data given video content complexity across the corpus of the video hosting platform. Complexity features of the video data are processed using the learning model to determine a rate-distortion cluster prediction for the video data, and transcoding parameters for transcoding the video data are selected based on that prediction. The rate-distortion clusters are modeled during the training of the learning model, such as based on rate-distortion curves of video data of the corpus of the video hosting platform and based on classifications of such video data. This approach minimizes total corpus egress and/or storage while further maintaining uniformity in the delivered quality of videos by the video hosting platform.

公开(公告)号：US20240009556A1

公开(公告)日：2024-01-11

申请号：US18217776

申请日：2023-07-03

Applicant: GOOGLE LLC

Inventor： Danny Hong ,  Sam John

IPC: A63F13/355

CPC classification number: A63F13/355 ,  A63F2300/538

Abstract: A cloud-based gaming server renders a set of game frames at a first frame rate for a current client gaming session. An encoder of the server then determines whether the first frame rate is lower than a second frame rate associated with the encoder. In response to the first frame rate being lower, the encoder is configured to generate skip frames, with each skip frame indicating that a game frame of the set of game frames is to be repeated. The encoder also encodes the set of game frames to produce a set of encoded game frames and inserts one or more skip frames between two or more encoded game frames of the set of encoded game frames to produce a game stream. The server then packetizes the game stream and transmits the packetized game stream to a client system associated with the current client system.

公开(公告)号：US10194188B1

公开(公告)日：2019-01-29

申请号：US15831163

申请日：2017-12-04

Applicant: Google LLC

Inventor： Sang-Uok Kum ,  Sam John ,  Thierry Foucu ,  Lei Yang ,  Alexander Jay Converse ,  Steve Benting

IPC: H04N21/2662 ,  H04N19/61 ,  H04N19/172 ,  H04N19/124 ,  H04N19/132 ,  H04N19/159 ,  H04L29/06 ,  H04N21/234

Abstract: Videos associated with video resolutions may be received. A first bitrate for each of the video resolutions may be identified based on a first bitrate point associated with the videos where a quality of the videos at a first video resolution that is upscaled to a second video resolution is better than a quality of the videos at the second video resolution at bitrates below the first bitrate point. The upscaling of the first video resolution may correspond to converting the videos from the first video resolution to the second video resolution at a client device. The identified corresponding first bitrate may be assigned to each of the video resolutions.

公开(公告)号：US20180084254A1

公开(公告)日：2018-03-22

申请号：US15784516

申请日：2017-10-16

Applicant: GOOGLE LLC

Inventor： Yao-Chung Lin ,  Sam John ,  Thierry Foucu ,  Sasi Inguva

IPC: H04N19/134 ,  H04N19/142

CPC classification number: H04N19/134 ,  H04N19/00472 ,  H04N19/00587 ,  H04N19/00921 ,  H04N19/142 ,  H04N19/40 ,  H04N19/87

Abstract: Systems and methods for processing a video sequence are disclosed. In accordance with some implementations, The method includes determining a first set of shot-change locations associated with a cut transition in a video sequence based on variance data defined in an encoding log associated with at least one previously encoded video frame. The method further includes determining a second set of shot-change locations associated with a fading transition in the video sequence based on the variance data defined in the encoding log associated with the at least one previously encoded video frame. The method also includes processing the video sequence based on at least a portion of the first set of shot-change locations and the second set of shot-change locations.

公开(公告)号：US12256071B2

公开(公告)日：2025-03-18

申请号：US18507279

申请日：2023-11-13

Applicant: GOOGLE LLC

Inventor： Di Chen ,  Sam John

IPC: H04N19/119 ,  H04N19/146 ,  H04N19/159

Abstract: Bitrate-adaptive segmentation is performed for transcoding a video stream uploaded to an online video platform for hosting and later playback to platform users. The video stream is segmented into chunks based on prediction-based bit costs determined for frames of the video stream rather than based on scene changes detected within the video stream. The bitrate-adaptive segmentation includes determining inter-prediction bit costs and intra-prediction bit costs for frames of the video stream based on information indicated within a pass log based on a first pass encoding of the video stream, determining chunk boundaries for segmenting the video stream into a chunk based on the inter-prediction bit costs and the intra-prediction bit costs for the frames, and transcoding the chunk to produce a transcoded video stream.

公开(公告)号：US11818345B2

公开(公告)日：2023-11-14

申请号：US17696760

申请日：2022-03-16

Applicant: GOOGLE LLC

Inventor： Di Chen ,  Sam John

IPC: H04N19/119 ,  H04N19/146 ,  H04N19/159

CPC classification number: H04N19/119 ,  H04N19/146 ,  H04N19/159

Abstract: Bitrate-adaptive segmentation is performed for transcoding a video stream uploaded to an online video platform for hosting and later playback to platform users. The video stream is segmented into chunks based on prediction-based bit costs determined for frames of the video stream rather than based on scene changes detected within the video stream. The bitrate-adaptive segmentation includes determining inter-prediction bit costs and intra-prediction bit costs for frames of the video stream based on information indicated within a pass log based on a first pass encoding of the video stream, determining chunk boundaries for segmenting the video stream into a chunk based on the inter-prediction bit costs and the intra-prediction bit costs for the frames, and transcoding the chunk to produce a transcoded video stream.