公开(公告)号：US20230137209A1

公开(公告)日：2023-05-04

申请号：US17518471

申请日：2021-11-03

Applicant: Adobe Inc.

Inventor： Sharmila Reddy Nangi ,  Niyati Himanshu Chhaya ,  Hyman Chung ,  Harshit Nyati ,  Nikhil Kaushik ,  Sopan Khosla

IPC: G06F40/253 ,  G06F40/30 ,  G06F40/166 ,  G06F3/0484 ,  G06F40/151

Abstract: A text style transfer system is described that generates different stylized versions of input text by rewriting the input text according to a target style. To do so, the text style transfer system employs a variational autoencoder to derive separate content and style representations for the input text, where the content representation specifies semantic information conveyed by the input text and the style representation specifies one or more style attributes expressed by the input text. The style representation using counterfactual reasoning to identify different transfer strengths for applying the target style to the input text. Each transfer strength represents a minimum change to the input text that achieves a different expression of the target style. The transfer strengths are then used to generate style representation variants, which are each concatenated with the content representation of the input text to generate the plurality of different stylized versions of the input text.

公开(公告)号：US20230325981A1

公开(公告)日：2023-10-12

申请号：US17718579

申请日：2022-04-12

Applicant: Adobe Inc.

Inventor： Aarsh Prakash Agarwal ,  Harshit Nyati

IPC: G06T5/00

CPC classification number: G06T5/002 ,  G06T2207/20172 ,  G06T2207/20081

Abstract: In implementations of systems for single image reflection removal, a computing device implements a removal system to receive data describing a digital image that depicts light reflected by a surface and light transmitted through the surface. The removal system predicts an edge map of a transmitted image for the light transmitted through the surface by processing the data using a first machine learning model trained on a first type of training data. A reflected component is predicted for the light reflected by the surface by processing the data using a second machine learning model trained on a second type of training data. A corrected digital image is generated that does not depict the light reflected by the surface based on the data, the edge map of the transmitted image, and the reflected component.

公开(公告)号：US12112130B2

公开(公告)日：2024-10-08

申请号：US17518471

申请日：2021-11-03

Applicant: Adobe Inc.

Inventor： Sharmila Reddy Nangi ,  Niyati Himanshu Chhaya ,  Hyman Chung ,  Harshit Nyati ,  Nikhil Kaushik ,  Sopan Khosla

IPC: G06F40/253 ,  G06F3/04847 ,  G06F40/151 ,  G06F40/166 ,  G06F40/30

CPC classification number: G06F40/253 ,  G06F3/04847 ,  G06F40/151 ,  G06F40/166 ,  G06F40/30

Abstract: A text style transfer system is described that generates different stylized versions of input text by rewriting the input text according to a target style. To do so, the text style transfer system employs a variational autoencoder to derive separate content and style representations for the input text, where the content representation specifies semantic information conveyed by the input text and the style representation specifies one or more style attributes expressed by the input text. The style representation using counterfactual reasoning to identify different transfer strengths for applying the target style to the input text. Each transfer strength represents a minimum change to the input text that achieves a different expression of the target style. The transfer strengths are then used to generate style representation variants, which are each concatenated with the content representation of the input text to generate the plurality of different stylized versions of the input text.