公开(公告)号：US11663467B2

公开(公告)日：2023-05-30

申请号：US16691110

申请日：2019-11-21

Applicant: ADOBE INC.

Inventor： Long Mai ,  Yannick Hold-Geoffroy ,  Naoto Inoue ,  Daichi Ito ,  Brian Lynn Price

IPC: G06N3/08 ,  G06T15/80 ,  G06T15/50 ,  G06T5/50

CPC classification number: G06N3/08 ,  G06T5/50 ,  G06T15/506 ,  G06T15/80 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Embodiments of the present invention provide systems, methods, and non-transitory computer storage media for generating an ambient occlusion (AO) map for a 2D image that can be combined with the 2D image to adjust the contrast of the 2D image based on the geometric information in the 2D image. In embodiments, using a trained neural network, an AO map for a 2D image is automatically generated without any predefined 3D scene information. Optimizing the neural network to generate an estimated AO map for a 2D image requires training, testing, and validating the neural network using a synthetic dataset comprised of pairs of images and ground truth AO maps rendered from 3D scenes. By using an estimated AO map to adjust the contrast of a 2D image, the contrast of the image can be adjusted to make the image appear lifelike by modifying the shadows and shading in the image based on the ambient lighting present in the image.

公开(公告)号：US10922860B2

公开(公告)日：2021-02-16

申请号：US16410854

申请日：2019-05-13

Applicant: Adobe Inc.

Inventor： Brian Price ,  Ning Xu ,  Naoto Inoue ,  Jimei Yang ,  Daicho Ito

IPC: G06T11/20 ,  G06K9/46 ,  G06K9/62 ,  G06T7/40 ,  G06T5/00

Abstract: Computing systems and computer-implemented methods can be used for automatically generating a digital line drawing of the contents of a photograph. In various examples, these techniques include use of a neural network, referred to as a generator network, that is trained on a dataset of photographs and human-generated line drawings of the photographs. The training data set teaches the neural network to trace the edges and features of objects in the photographs, as well as which edges or features can be ignored. The output of the generator network is a two-tone digital image, where the background of the image is one tone, and the contents in the input photographs are represented by lines drawn in the second tone. In some examples, a second neural network, referred to as a restorer network, can further process the output of the generator network, and remove visual artifacts and clean up the lines.

公开(公告)号：US12147896B2

公开(公告)日：2024-11-19

申请号：US18296525

申请日：2023-04-06

Applicant: Adobe Inc.

Inventor： Long Mai ,  Yannick Hold-Geoffroy ,  Naoto Inoue ,  Daichi Ito ,  Brian Lynn Price

IPC: G06T15/80 ,  G06N3/08 ,  G06T5/50 ,  G06T15/50

Abstract: Embodiments of the present invention provide systems, methods, and non-transitory computer storage media for generating an ambient occlusion (AO) map for a 2D image that can be combined with the 2D image to adjust the contrast of the 2D image based on the geometric information in the 2D image. In embodiments, using a trained neural network, an AO map for a 2D image is automatically generated without any predefined 3D scene information. Optimizing the neural network to generate an estimated AO map for a 2D image requires training, testing, and validating the neural network using a synthetic dataset comprised of pairs of images and ground truth AO maps rendered from 3D scenes. By using an estimated AO map to adjust the contrast of a 2D image, the contrast of the image can be adjusted to make the image appear lifelike by modifying the shadows and shading in the image based on the ambient lighting present in the image.

公开(公告)号：US20230244940A1

公开(公告)日：2023-08-03

申请号：US18296525

申请日：2023-04-06

Applicant: Adobe Inc.

Inventor： Long MAI ,  Yannick Hold-Geoffroy ,  Naoto Inoue ,  Daichi Ito ,  Brian Lynn Price

IPC: G06N3/08 ,  G06T15/80 ,  G06T15/50 ,  G06T5/50

CPC classification number: G06N3/08 ,  G06T15/80 ,  G06T15/506 ,  G06T5/50 ,  G06T2207/20084 ,  G06T2207/10028 ,  G06T2207/20081

Abstract: Embodiments of the present invention provide systems, methods, and non-transitory computer storage media for generating an ambient occlusion (AO) map for a 2D image that can be combined with the 2D image to adjust the contrast of the 2D image based on the geometric information in the 2D image. In embodiments, using a trained neural network, an AO map for a 2D image is automatically generated without any predefined 3D scene information. Optimizing the neural network to generate an estimated AO map for a 2D image requires training, testing, and validating the neural network using a synthetic dataset comprised of pairs of images and ground truth AO maps rendered from 3D scenes. By using an estimated AO map to adjust the contrast of a 2D image, the contrast of the image can be adjusted to make the image appear lifelike by modifying the shadows and shading in the image based on the ambient lighting present in the image.