公开(公告)号：US11972534B2

公开(公告)日：2024-04-30

申请号：US17519841

申请日：2021-11-05

Applicant: Adobe Inc.

Inventor： Maxine Perroni-Scharf ,  Yannick Hold-Geoffroy ,  Kalyan Sunkavalli ,  Jonathan Eisenmann

IPC: G06T19/20 ,  G06F18/211 ,  G06F18/22 ,  G06N3/02 ,  G06T15/04

CPC classification number: G06T19/20 ,  G06F18/211 ,  G06F18/22 ,  G06N3/02 ,  G06T15/04 ,  G06T2219/2004 ,  G06T2219/2016

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a visual neural network to replace materials in a three-dimensional scene with visually similar materials from a source dataset. Specifically, the disclosed system utilizes the visual neural network to generate source deep visual features representing source texture maps from materials in a plurality of source materials. Additionally, the disclosed system utilizes the visual neural network to generate deep visual features representing texture maps from materials in a digital scene. The disclosed system then determines source texture maps that are visually similar to the texture maps of the digital scene based on visual similarity metrics that compare the source deep visual features and the deep visual features. Additionally, the disclosed system modifies the digital scene by replacing one or more of the texture maps in the digital scene with the visually similar source texture maps.

公开(公告)号：US20230141395A1

公开(公告)日：2023-05-11

申请号：US17519841

申请日：2021-11-05

Applicant: Adobe Inc.

Inventor： Maxine Perroni-Scharf ,  Yannick Hold-Geoffroy ,  Kalyan Sunkavalli ,  Jonathan Eisenmann

IPC: G06T19/20 ,  G06T15/04 ,  G06K9/62 ,  G06N3/02

CPC classification number: G06T19/20 ,  G06K9/6215 ,  G06K9/6228 ,  G06N3/02 ,  G06T15/04 ,  G06T2219/2004 ,  G06T2219/2016

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a visual neural network to replace materials in a three-dimensional scene with visually similar materials from a source dataset. Specifically, the disclosed system utilizes the visual neural network to generate source deep visual features representing source texture maps from materials in a plurality of source materials. Additionally, the disclosed system utilizes the visual neural network to generate deep visual features representing texture maps from materials in a digital scene. The disclosed system then determines source texture maps that are visually similar to the texture maps of the digital scene based on visual similarity metrics that compare the source deep visual features and the deep visual features. Additionally, the disclosed system modifies the digital scene by replacing one or more of the texture maps in the digital scene with the visually similar source texture maps.