公开(公告)号：US20250045641A1

公开(公告)日：2025-02-06

申请号：US18229593

申请日：2023-08-02

Applicant: Adobe Inc.

Inventor： Kanak MAHADIK ,  Jashwant Raj GUNASEKARAN ,  Haoliang WANG ,  Vani NAGARAJAN

IPC: G06N20/20

Abstract: In various examples, a prediction machine learning model determines a set of computing instances capable of executing a machine learning model and a set of batch sizes associated with inferencing requests based on a set of model parameters associated with the machine learning model and a number of floating point operations (FLOPS). In such examples this information is used to update a user interface to indicate computing instances to perform inferencing operations.

公开(公告)号：US20240314293A1

公开(公告)日：2024-09-19

申请号：US18669137

申请日：2024-05-20

Applicant: Adobe Inc.

Inventor： Stefano PETRANGELI ,  Viswanathan SWAMINATHAN ,  Haoliang WANG

IPC: H04N19/105 ,  H04N19/176 ,  H04N19/182 ,  H04N19/91

CPC classification number: H04N19/105 ,  H04N19/176 ,  H04N19/182 ,  H04N19/91

Abstract: Embodiments are disclosed for lossless image compression using block-based prediction and context adaptive entropy coding. A method of lossless image compression using block-based prediction and context adaptive entropy coding comprises dividing an input image into a plurality of blocks, determining a pixel predictor for each block based on a block strategy, determining a plurality of residual values using the pixel predictor for each block, selecting a subset of features associated with the plurality of residual values, performing context modeling on the plurality of residual values based on the subset of features to identify a plurality of residual clusters, and entropy coding the plurality of residual clusters.

公开(公告)号：US20220400253A1

公开(公告)日：2022-12-15

申请号：US17891057

申请日：2022-08-18

Applicant: Adobe Inc.

Inventor： Stefano PETRANGELI ,  Viswanathan SWAMINATHAN ,  Haoliang WANG

IPC: H04N19/105 ,  H04N19/182 ,  H04N19/91 ,  H04N19/176

Abstract: Embodiments are disclosed for lossless image compression using block-based prediction and context adaptive entropy coding. A method of lossless image compression using block-based prediction and context adaptive entropy coding comprises dividing an input image into a plurality of blocks, determining a pixel predictor for each block based on a block strategy, determining a plurality of residual values using the pixel predictor for each block, selecting a subset of features associated with the plurality of residual values, performing context modeling on the plurality of residual values based on the subset of features to identify a plurality of residual clusters, and entropy coding the plurality of residual clusters.

公开(公告)号：US20220264084A1

公开(公告)日：2022-08-18

申请号：US17177592

申请日：2021-02-17

Applicant: Adobe Inc.

Inventor： Stefano PETRANGELI ,  Viswanathan SWAMINATHAN ,  Haoliang WANG

IPC: H04N19/105 ,  H04N19/176 ,  H04N19/91 ,  H04N19/182

Abstract: Embodiments are disclosed for lossless image compression using block-based prediction and context adaptive entropy coding. A method of lossless image compression using block-based prediction and context adaptive entropy coding comprises dividing an input image into a plurality of blocks, determining a pixel predictor for each block based on a block strategy, determining a plurality of residual values using the pixel predictor for each block, selecting a subset of features associated with the plurality of residual values, performing context modeling on the plurality of residual values based on the subset of features to identify a plurality of residual clusters, and entropy coding the plurality of residual clusters.