公开(公告)号：US12079957B2

公开(公告)日：2024-09-03

申请号：US17582266

申请日：2022-01-24

Applicant: Adobe Inc.

Inventor： Michael Gharbi ,  Camille Biscarrat

IPC: G06K9/00 ,  G06N3/08 ,  G06T5/50 ,  G06T7/33

CPC classification number: G06T5/50 ,  G06N3/08 ,  G06T7/337 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20212

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize a continuous kernel neural network that learns continuous reconstruction kernels to merge digital image samples in local neighborhoods and generate enhanced digital images from a plurality of burst digital images. For example, the disclosed systems can utilize an alignment model to align image samples from burst digital images to a common coordinate system (e.g., without resampling). In some embodiments, the disclosed systems generate localized latent vector representations of kernel neighborhoods and determines continuous displacement vectors between the image samples and output pixels of the enhanced digital image. The disclosed systems can utilize the continuous kernel network together with the latent vector representations and continuous displacement vectors to generated learned kernel weights for combining the image samples and generating an enhanced digital image.

公开(公告)号：US20230237628A1

公开(公告)日：2023-07-27

申请号：US17582266

申请日：2022-01-24

Applicant: Adobe Inc.

Inventor： Michael Gharbi ,  Camille Biscarrat

IPC: G06T5/50 ,  G06T7/33 ,  G06N3/08

CPC classification number: G06T5/50 ,  G06T7/337 ,  G06N3/08 ,  G06T2207/20212 ,  G06T2207/20084 ,  G06T2207/20081

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize a continuous kernel neural network that learns continuous reconstruction kernels to merge digital image samples in local neighborhoods and generate enhanced digital images from a plurality of burst digital images. For example, the disclosed systems can utilize an alignment model to align image samples from burst digital images to a common coordinate system (e.g., without resampling). In some embodiments, the disclosed systems generate localized latent vector representations of kernel neighborhoods and determines continuous displacement vectors between the image samples and output pixels of the enhanced digital image. The disclosed systems can utilize the continuous kernel network together with the latent vector representations and continuous displacement vectors to generated learned kernel weights for combining the image samples and generating an enhanced digital image.