-
公开(公告)号：US11575947B2
公开(公告)日：2023-02-07
申请号：US17338764
申请日：2021-06-04
Applicant: Adobe Inc.
Inventor： Viswanathan Swaminathan , Saayan Mitra , Akshay Malhotra
IPC: H04N19/94 , H04N19/46 , H04N19/91 , H04N21/274 , G06T9/00
Abstract: Residual vectors are compressed in a lossless compression scheme suitable for cloud DVR video content applications. Thus, a cloud DVR service provider can take many copies of the same file stored in the cloud and save storage space by compressing those copies while still maintaining their status as distinct copies, one per user. Vector quantization is used for compressing already-compressed video streams (e.g., MPEG streams). As vector quantization is a lossy compression scheme, the residual vector has to be stored to regenerate the original video stream at the decoding (playback) node. Entropy coding schemes like Arithmetic or Huffman coding can be used to compress the residual vectors. Additional strategies can be implemented to further optimize this residual compression. In some embodiments, the techniques operate to provide a 25-50% improvement in compression. Storage space is thus more efficiently used and video transmission may be faster in some cases.
-
Patent Agency Ranking
公开(公告)号：US20210272341A1
公开(公告)日：2021-09-02
申请号：US16804822
申请日：2020-02-28
Applicant: Adobe Inc.
Inventor： Viswanathan Swaminathan , Gang Wu , Akshay Malhotra
Abstract: Generating images and videos depicting a human subject wearing textually defined attire is described. An image generation system receives a two-dimensional reference image depicting a person and a textual description describing target clothing in which the person is to be depicted as wearing. To maintain a personal identity of the person, the image generation system implements a generative model, trained using both discriminator loss and perceptual quality loss, which is configured to generate images from text. In some implementations, the image generation system is configured to train the generative model to output visually realistic images depicting the human subject in the target clothing. The image generation system is further configured to apply the trained generative model to process individual frames of a reference video depicting a person and output frames depicting the person wearing textually described target clothing.
-
公开(公告)号：US11032578B2
公开(公告)日：2021-06-08
申请号：US16020018
申请日：2018-06-27
Applicant: Adobe Inc.
Inventor： Viswanathan Swaminathan , Saayan Mitra , Akshay Malhotra
IPC: H04N7/12 , H04N19/94 , H04N19/46 , H04N19/91 , H04N21/274
Abstract: Residual vectors are compressed in a lossless compression scheme suitable for cloud DVR video content applications. Thus, a cloud DVR service provider can take many copies of the same file stored in the cloud and save storage space by compressing those copies while still maintaining their status as distinct copies, one per user. Vector quantization is used for compressing already-compressed video streams (e.g., MPEG streams). As vector quantization is a lossy compression scheme, the residual vector has to be stored to regenerate the original video stream at the decoding (playback) node. Entropy coding schemes like Arithmetic or Huffman coding can be used to compress the residual vectors. Additional strategies can be implemented to further optimize this residual compression. In some embodiments, the techniques operate to provide a 25-50% improvement in compression. Storage space is thus more efficiently used and video transmission may be faster in some cases.
-
公开(公告)号：US11783486B2
公开(公告)日：2023-10-10
申请号：US17553114
申请日：2021-12-16
Applicant: Adobe Inc.
Inventor： Viswanathan Swaminathan , Gang Wu , Akshay Malhotra
IPC: G06T7/00 , G06T7/11 , G06T11/60 , G06T7/70 , G06N3/08 , G06V40/10 , G06F18/214 , G06F18/21 , G06V10/774 , G06V10/776 , G06V10/82
CPC classification number: G06T7/11 , G06F18/214 , G06F18/217 , G06N3/08 , G06T7/70 , G06T11/60 , G06V10/774 , G06V10/776 , G06V10/82 , G06V40/10 , G06V40/103 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084 , G06T2207/30168 , G06T2207/30196
Abstract: Generating images and videos depicting a human subject wearing textually defined attire is described. An image generation system receives a two-dimensional reference image depicting a person and a textual description describing target clothing in which the person is to be depicted as wearing. To maintain a personal identity of the person, the image generation system implements a generative model, trained using both discriminator loss and perceptual quality loss, which is configured to generate images from text. In some implementations, the image generation system is configured to train the generative model to output visually realistic images depicting the human subject in the target clothing. The image generation system is further configured to apply the trained generative model to process individual frames of a reference video depicting a person and output frames depicting the person wearing textually described target clothing.
-
公开(公告)号：US20220108509A1
公开(公告)日：2022-04-07
申请号：US17553114
申请日：2021-12-16
Applicant: Adobe Inc.
Inventor： Viswanathan Swaminathan , Gang Wu , Akshay Malhotra
Abstract: Generating images and videos depicting a human subject wearing textually defined attire is described. An image generation system receives a two-dimensional reference image depicting a person and a textual description describing target clothing in which the person is to be depicted as wearing. To maintain a personal identity of the person, the image generation system implements a generative model, trained using both discriminator loss and perceptual quality loss, which is configured to generate images from text. In some implementations, the image generation system is configured to train the generative model to output visually realistic images depicting the human subject in the target clothing. The image generation system is further configured to apply the trained generative model to process individual frames of a reference video depicting a person and output frames depicting the person wearing textually described target clothing.
-
公开(公告)号：US11210831B2
公开(公告)日：2021-12-28
申请号：US16804822
申请日：2020-02-28
Applicant: Adobe Inc.
Inventor： Viswanathan Swaminathan , Gang Wu , Akshay Malhotra
Abstract: Generating images and videos depicting a human subject wearing textually defined attire is described. An image generation system receives a two-dimensional reference image depicting a person and a textual description describing target clothing in which the person is to be depicted as wearing. To maintain a personal identity of the person, the image generation system implements a generative model, trained using both discriminator loss and perceptual quality loss, which is configured to generate images from text. In some implementations, the image generation system is configured to train the generative model to output visually realistic images depicting the human subject in the target clothing. The image generation system is further configured to apply the trained generative model to process individual frames of a reference video depicting a person and output frames depicting the person wearing textually described target clothing.
-
-
-
-
-
Search Results
6
records
(took 0.016 seconds)
