公开(公告)号：US11189066B1

公开(公告)日：2021-11-30

申请号：US16188626

申请日：2018-11-13

Applicant: ADOBE INC.

Inventor： Zoya Bylinskii ,  Aaron Hertzmann ,  Bryan Russell

IPC: G06T11/60 ,  G06N3/02 ,  G06T11/00

Abstract: Embodiments disclosed herein describe systems, methods, and products that train one or more neural networks and execute the trained neural network across various applications. The one or more neural networks are trained to optimize a loss function comprising a pixel-level comparison between the outputs generated by the neural networks and the ground truth dataset generated from a bubble view methodology or an explicit importance maps methodology. Each of these methodologies may be more efficient than and may closely approximate the more expensive but accurate human eye gaze measurements. The embodiments herein leverage an existing process for training neural networks to generate importance maps of a plurality of graphic objects to offer interactive applications for graphics designs and data visualizations. Based on the importance maps, the computer may provide real-time design feedback, generate smart thumbnails of the graphic objects, provide recommendations for design retargeting, and extract smart color themes from the graphic objects.

公开(公告)号：US20200151938A1

公开(公告)日：2020-05-14

申请号：US16184289

申请日：2018-11-08

Applicant: Adobe Inc.

Inventor： Elya Shechtman ,  Yijun Li ,  Chen Fang ,  Aaron Hertzmann

IPC: G06T15/02 ,  G06T15/80 ,  G06N3/04 ,  G06N3/08

Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that integrate (or embed) a non-photorealistic rendering (“NPR”) generator with a style-transfer-neural network to generate stylized images that both correspond to a source image and resemble a stroke style. By integrating an NPR generator with a style-transfer-neural network, the disclosed methods, non-transitory computer readable media, and systems can accurately capture a stroke style resembling one or both of stylized edges or stylized shadings. When training such a style-transfer-neural network, the integrated NPR generator can enable the disclosed methods, non-transitory computer readable media, and systems to use real-stroke drawings (instead of conventional paired-ground-truth drawings) for training the network to accurately portray a stroke style. In some implementations, the disclosed methods, non-transitory computer readable media, and systems can either train or apply a style-transfer-neural network that captures a variety of stroke styles, such as different edge-stroke styles or shading-stroke styles.

公开(公告)号：US10467760B2

公开(公告)日：2019-11-05

申请号：US15440572

申请日：2017-02-23

Applicant: Adobe Inc.

Inventor： Vladimir Kim ,  Aaron Hertzmann ,  Mehmet Yumer ,  Li Yi

IPC: G06T7/162 ,  G06T7/11

Abstract: This disclosure involves generating and outputting a segmentation model using 3D models having user-provided labels and scene graphs. For example, a system uses a neural network learned from the user-provided labels to transform feature vectors, which represent component shapes of the 3D models, into transformed feature vectors identifying points in a feature space. The system identifies component-shape groups from clusters of the points in the feature space. The system determines, from the scene graphs, parent-child relationships for the component-shape groups. The system generates a segmentation hierarchy with nodes corresponding to the component-shape groups and links corresponding to the parent-child relationships. The system trains a point classifier to assign feature points, which are sampled from an input 3D shape, to nodes of the segmentation hierarchy, and thereby segment the input 3D shape into component shapes.