公开(公告)号：US20240144583A1

公开(公告)日：2024-05-02

申请号：US18398009

申请日：2023-12-27

Applicant: Google LLC

Inventor： Philip Andrew Chou ,  Berivan Isik ,  Sung Jin Hwang ,  Nicholas Milo Johnston ,  George Dan Toderici

IPC: G06T15/08 ,  H04N19/176 ,  H04N19/46

CPC classification number: G06T15/08 ,  H04N19/176 ,  H04N19/46

Abstract: Example embodiments of the present disclosure relate to systems and methods for compressing attributes of volumetric and hypervolumetric datasets. An example system performs operations including obtaining a reference dataset comprising attributes indexed by a domain of multidimensional coordinates; subdividing the domain into a plurality of blocks respectively associated with a plurality of attribute subsets; inputting, to a local nonlinear operator, a latent representation for an attribute subset associated with at least one block of the plurality of blocks; obtaining, using the local nonlinear operator and based on the latent representation, an attribute representation of one or more attributes of the attribute subset; and updating the latent representation based on a comparison of the attribute representation and the reference dataset.

公开(公告)号：US20230260197A1

公开(公告)日：2023-08-17

申请号：US17708628

申请日：2022-03-30

Applicant: Google LLC

Inventor： Philip Andrew Chou ,  Berivan Isik ,  Sung Jin Hwang ,  Nicholas Milo Johnston ,  George Dan Toderici

IPC: G06T15/08 ,  H04N19/46 ,  H04N19/176

CPC classification number: G06T15/08 ,  H04N19/46 ,  H04N19/176

Abstract: Example embodiments of the present disclosure relate to systems and methods for compressing attributes of volumetric and hypervolumetric datasets. An example system performs operations including obtaining a reference dataset comprising attributes indexed by a domain of multidimensional coordinates; subdividing the domain into a plurality of blocks respectively associated with a plurality of attribute subsets; inputting, to a local nonlinear operator, a latent representation for an attribute subset associated with at least one block of the plurality of blocks; obtaining, using the local nonlinear operator and based on the latent representation, an attribute representation of one or more attributes of the attribute subset; and updating the latent representation based on a comparison of the attribute representation and the reference dataset.

公开(公告)号：US20250045968A1

公开(公告)日：2025-02-06

申请号：US18570562

申请日：2021-06-16

Applicant: Google LLC

Inventor： Onur G. Guleryuz ,  Ruofei Du ,  Hugues H. Hoppe ,  Sean Ryan Francesco Fanello ,  Philip Andrew Chou ,  Danhang Tang ,  Philip Davidson

IPC: G06T9/00 ,  G06V10/82

Abstract: Nonlinear peri-codec optimization for image and video coding includes obtaining a source image including pixel values expressed in a first defined image sample space, generating a neuralized image representing the source image, the neuralized image including pixel values that are expressed as neural latent space values, encoding the input image wherein the neural latent space values are used as pixel values in a second defined image sample space and the input image is in an operative image format of the encoder, such that a decoder decodes the encoded image to obtain a reconstructed image in the second defined image sample space, wherein the reconstructed image is a reconstructed neuralized image including reconstructed neural latent space values, such that a deneuralized reconstructed image corresponding to the source image is obtained by a nonlinear post-codec image processor in the first defined image sample space.

公开(公告)号：US11900525B2

公开(公告)日：2024-02-13

申请号：US17708628

申请日：2022-03-30

Applicant: Google LLC

Inventor： Philip Andrew Chou ,  Berivan Isik ,  Sung Jin Hwang ,  Nicholas Milo Johnston ,  George Dan Toderici

IPC: G06T15/08 ,  H04N19/176 ,  H04N19/46

CPC classification number: G06T15/08 ,  H04N19/176 ,  H04N19/46

Abstract: Example embodiments of the present disclosure relate to systems and methods for compressing attributes of volumetric and hypervolumetric datasets. An example system performs operations including obtaining a reference dataset comprising attributes indexed by a domain of multidimensional coordinates; subdividing the domain into a plurality of blocks respectively associated with a plurality of attribute subsets; inputting, to a local nonlinear operator, a latent representation for an attribute subset associated with at least one block of the plurality of blocks; obtaining, using the local nonlinear operator and based on the latent representation, an attribute representation of one or more attributes of the attribute subset; and updating the latent representation based on a comparison of the attribute representation and the reference dataset.