公开(公告)号：US11798180B2

公开(公告)日：2023-10-24

申请号：US17186436

申请日：2021-02-26

Applicant: Adobe Inc.

Inventor： Wei Yin ,  Jianming Zhang ,  Oliver Wang ,  Simon Niklaus ,  Mai Long ,  Su Chen

IPC: G06T7/50 ,  G06T7/593 ,  G06T7/30 ,  G06T7/13 ,  G06T7/143 ,  G06T7/521

CPC classification number: G06T7/50 ,  G06T7/13 ,  G06T7/143 ,  G06T7/30 ,  G06T7/521 ,  G06T7/593 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: This disclosure describes one or more implementations of a depth prediction system that generates accurate depth images from single input digital images. In one or more implementations, the depth prediction system enforces different sets of loss functions across mix-data sources to generate a multi-branch architecture depth prediction model. For instance, in one or more implementations, the depth prediction model utilizes different data sources having different granularities of ground truth depth data to robustly train a depth prediction model. Further, given the different ground truth depth data granularities from the different data sources, the depth prediction model enforces different combinations of loss functions including an image-level normalized regression loss function and/or a pair-wise normal loss among other loss functions.

公开(公告)号：US11676279B2

公开(公告)日：2023-06-13

申请号：US17126986

申请日：2020-12-18

Applicant: Adobe Inc.

Inventor： Brian Price ,  Su Chen ,  Shuo Yang

IPC: G06K9/00 ,  G06T7/11 ,  G06T7/143 ,  G06T7/136 ,  G06T7/162 ,  G06T7/90 ,  G06N3/088 ,  G06N3/045

CPC classification number: G06T7/11 ,  G06N3/045 ,  G06N3/088 ,  G06T7/136 ,  G06T7/143 ,  G06T7/162 ,  G06T7/90 ,  G06T2200/24 ,  G06T2207/20072 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20092

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that utilize a deep neural network to process object user indicators and an initial object segmentation from a digital image to efficiently and flexibly generate accurate object segmentations. In particular, the disclosed systems can determine an initial object segmentation for the digital image (e.g., utilizing an object segmentation model or interactive selection processes). In addition, the disclosed systems can identify an object user indicator for correcting the initial object segmentation and generate a distance map reflecting distances between pixels of the digital image and the object user indicator. The disclosed systems can generate an image-interaction-segmentation triplet by combining the digital image, the initial object segmentation, and the distance map. By processing the image-interaction-segmentation triplet utilizing the segmentation neural network, the disclosed systems can provide an updated object segmentation for display to a client device.

公开(公告)号：US20220292654A1

公开(公告)日：2022-09-15

申请号：US17200338

申请日：2021-03-12

Applicant: Adobe Inc.

Inventor： He Zhang ,  Yifan Jiang ,  Yilin Wang ,  Jianming Zhang ,  Kalyan Sunkavalli ,  Sarah Kong ,  Su Chen ,  Sohrab Amirghodsi ,  Zhe Lin

IPC: G06T5/50 ,  G06T7/194 ,  G06T11/60 ,  G06T11/00 ,  G06N3/04 ,  G06N3/08

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately, efficiently, and flexibly generating harmonized digital images utilizing a self-supervised image harmonization neural network. In particular, the disclosed systems can implement, and learn parameters for, a self-supervised image harmonization neural network to extract content from one digital image (disentangled from its appearance) and appearance from another from another digital image (disentangled from its content). For example, the disclosed systems can utilize a dual data augmentation method to generate diverse triplets for parameter learning (including input digital images, reference digital images, and pseudo ground truth digital images), via cropping a digital image with perturbations using three-dimensional color lookup tables (“LUTs”). Additionally, the disclosed systems can utilize the self-supervised image harmonization neural network to generate harmonized digital images that depict content from one digital image having the appearance of another digital image.

公开(公告)号：US20220277514A1

公开(公告)日：2022-09-01

申请号：US17186522

申请日：2021-02-26

Applicant: Adobe Inc.

Inventor： Wei Yin ,  Jianming Zhang ,  Oliver Wang ,  Simon Niklaus ,  Mai Long ,  Su Chen

IPC: G06T17/00 ,  G06K9/00 ,  G06N3/04 ,  G06T7/80

Abstract: This disclosure describes implementations of a three-dimensional (3D) scene recovery system that reconstructs a 3D scene representation of a scene portrayed in a single digital image. For instance, the 3D scene recovery system trains and utilizes a 3D point cloud model to recover accurate intrinsic camera parameters from a depth map of the digital image. Additionally, the 3D point cloud model may include multiple neural networks that target specific intrinsic camera parameters. For example, the 3D point cloud model may include a depth 3D point cloud neural network that recovers the depth shift as well as include a focal length 3D point cloud neural network that recovers the camera focal length. Further, the 3D scene recovery system may utilize the recovered intrinsic camera parameters to transform the single digital image into an accurate and realistic 3D scene representation, such as a 3D point cloud.