公开(公告)号：US11367206B2

公开(公告)日：2022-06-21

申请号：US16790056

申请日：2020-02-13

Applicant: Adobe Inc.

Inventor： Zhe Lin ,  Oliver Wang ,  Mai Long ,  Ke Xian ,  Jianming Zhang

IPC: G06T7/00 ,  G06T7/50 ,  G06T7/13 ,  G06N3/08 ,  G06N3/04

Abstract: In order to provide monocular depth prediction, a trained neural network may be used. To train the neural network, edge detection on a digital image may be performed to determine at least one edge of the digital image, and then a first point and a second point of the digital image may be sampled, based on the at least one edge. A relative depth between the first point and the second point may be predicted, and the neural network may be trained to perform monocular depth prediction using a loss function that compares the predicted relative depth with a ground truth relative depth between the first point and the second point.

公开(公告)号：US11055828B2

公开(公告)日：2021-07-06

申请号：US16407915

申请日：2019-05-09

Applicant: Adobe Inc.

Inventor： Mai Long ,  Zhaowen Wang ,  Ning Xu ,  John Philip Collomosse ,  Haotian Zhang ,  Hailin Jin

IPC: G06T5/00 ,  G06N3/04 ,  G06K9/62

Abstract: Techniques of inpainting video content include training a neural network to perform an inpainting operation on a video using only content from that video. For example, upon receiving video content including a sequence of initial frames, a computer generates a sequence of inputs corresponding to at least some of the sequence of initial frames and each input including, for example, a uniform noise map. The computer then generates a convolutional neural network (CNN) using the sequence of input as the initial layer. The parameters of the CNN are adjusted according to a cost function, which has components including a flow generation loss component and a consistency loss component. The CNN then outputs, on a final layer, estimated image values in a sequence of final frames.

公开(公告)号：US11017586B2

公开(公告)日：2021-05-25

申请号：US16388187

申请日：2019-04-18

Applicant: ADOBE INC.

Inventor： Mai Long ,  Simon Niklaus ,  Jimei Yang

IPC: G06T15/20 ,  G06T7/10 ,  G06N3/04

Abstract: Systems and methods are described for generating a three dimensional (3D) effect from a two dimensional (2D) image. The methods may include generating a depth map based on a 2D image, identifying a camera path, generating one or more extremal views based on the 2D image and the camera path, generating a global point cloud by inpainting occlusion gaps in the one or more extremal views, generating one or more intermediate views based on the global point cloud and the camera path, and combining the one or more extremal views and the one or more intermediate views to produce a 3D motion effect.

公开(公告)号：US10346727B2

公开(公告)日：2019-07-09

申请号：US15429769

申请日：2017-02-10

Applicant: Adobe Inc.

Inventor： Zhe Lin ,  Mai Long ,  Jonathan Brandt ,  Hailin Jin ,  Chen Fang

IPC: G06K9/46 ,  G06K9/52 ,  G06K9/62 ,  G06K9/66 ,  G06K9/72 ,  G06N3/08 ,  G06F16/532

Abstract: The present disclosure includes methods and systems for searching for digital visual media based on semantic and spatial information. In particular, one or more embodiments of the disclosed systems and methods identify digital visual media displaying targeted visual content in a targeted region based on a query term and a query area provide via a digital canvas. Specifically, the disclosed systems and methods can receive user input of a query term and a query area and provide the query term and query area to a query neural network to generate a query feature set. Moreover, the disclosed systems and methods can compare the query feature set to digital visual media feature sets. Further, based on the comparison, the disclosed systems and methods can identify digital visual media portraying targeted visual content corresponding to the query term within a targeted region corresponding to the query area.