Brian E Price

US Patent:

8610712, Dec 17, 2013

Filed:

Jul 28, 2011

Appl. No.:

13/193303

Inventors:

Scott D. Cohen - Sunnyvale CA, US
Brian L. Price - San Jose CA, US

Assignee:

Adobe Systems Incorporated - San Jose CA

International Classification:

G06T 15/00
G06K 9/00
G06F 3/048

US Classification:

345419, 382154, 715852

Abstract:

A method is disclosed. Input data indicates a location within a region of a digital image of a stereo image pair. A boundary of the region and a corresponding boundary of a corresponding region of another digital image are defined based on the input data, content of the digital image, and content of the another digital image. The boundary and the corresponding boundary represent boundaries of a visual feature in the digital image and the other digital image. The defining further includes constructing a probability distribution for the digital image and another probability distribution for the other digital image. The probability distribution for the digital image represents a probability that each pixel of a set of pixels of the digital image is within the region. The other probability distribution represents a probability that each pixel of another set of pixels of the another digital image is within the corresponding region.

US Patent:

20130083021, Apr 4, 2013

Filed:

Sep 27, 2012

Appl. No.:

13/629309

Inventors:

Scott D. Cohen - Sunnyvale CA, US
Brian L. Price - San Jose CA, US
Chenxi Zhang - Lexington KY, US
Jonathan W. Brandt - Santa Cruz CA, US

International Classification:

G06T 17/00

US Classification:

345420

Abstract:

Embodiments of methods and systems for stereo-aware image editing are described. A three-dimensional model of a stereo scene is built from one or more input images. Camera parameters for the input images are computed. The three-dimensional model is modified. In some embodiments, the modifying the three-dimensional model includes modifying one or more of the images and applying results of the modifying one or more of the images to corresponding model vertices. The scene is re-rendered from the camera parameters to produce an edited stereo pair that is consistent with the three-dimensional model.

US Patent:

20130136338, May 30, 2013

Filed:

Nov 13, 2012

Appl. No.:

13/675905

Inventors:

ADOBE SYSTEMS INCORPORATED - San Jose CA, US
Scott D. Cohen - Sunnyvale CA, US
Brian L. Price - San Jose CA, US
Lesley Ann Northam - Picton, CA

Assignee:

ADOBE SYSTEMS INCORPORATED - San Jose CA

International Classification:

G06K 9/46

US Classification:

382154

Abstract:

Methods and apparatus for disparity map correction through statistical analysis on local neighborhoods. A disparity map correction technique may be used to correct mistakes in a disparity or depth map. The disparity map correction technique may detect and mark invalid pixel pairs in a disparity map, segment the image, and perform a statistical analysis of the disparities in each segment to identify outliers. The invalid and outlier pixels may then be corrected using other disparity values in the local neighborhood. Multiple iterations of the disparity map correction technique may be performed to further improve the output disparity map.

US Patent:

20220230321, Jul 21, 2022

Filed:

Jan 15, 2021

Appl. No.:

17/151111

Inventors:

- San Jose CA, US
Brian Price - San Jose CA, US
Scott Cohen - Sunnyvale CA, US

International Classification:

G06T 7/11
G06T 7/168
G06T 7/181
G06T 5/00
G06T 9/00

Abstract:

The present disclosure relates to a class-agnostic object segmentation system that automatically detects, segments, and selects objects within digital images irrespective of object semantic classifications. For example, the object segmentation system utilizes a class-agnostic object segmentation neural network to segment each pixel in a digital image into an object mask. Further, in response to detecting a selection request of a target object, the object segmentation system utilizes a corresponding object mask to automatically select the target object within the digital image. In some implementations, the object segmentation system utilizes a class-agnostic object segmentation neural network to detect and automatically select a partial object in the digital image in response to a target object selection request.

US Patent:

20210158139, May 27, 2021

Filed:

Nov 21, 2019

Appl. No.:

16/691110

Inventors:

- SAN JOSE CA, US
Naoto INOUE - Kanagawa, JP
Daichi ITO - Los Gatos CA, US
Brian Lynn PRICE - Pleasant Grove UT, US

International Classification:

G06N 3/08
G06T 15/80
G06T 15/50
G06T 5/50

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.

US Patent:

20210081766, Mar 18, 2021

Filed:

Sep 17, 2019

Appl. No.:

16/573342

Inventors:

- San Jose CA, US
Curtis Wigington - San Jose CA, US
Brian Price - Pleasant Grove UT, US

International Classification:

G06N 3/04
G06N 3/08
G06K 9/62
G06F 17/18

Abstract:

Described techniques for multi-label classification, in which sequential data includes characters that have two or more aspects that require classification, are capable of providing separate classifications for different categories of components. Using an appropriately-trained neural network, the described techniques perform aligning and otherwise combining two or more classifications (e.g., categories, or types of labels) to obtain multi-label characters.

US Patent:

20200410689, Dec 31, 2020

Filed:

Sep 14, 2020

Appl. No.:

17/020023

Inventors:

- San Jose CA, US
Brian Price - San Jose CA, US
Scott Cohen - Sunnyvale CA, US

International Classification:

G06T 7/11
G06T 7/194
G06T 7/73

Abstract:

A temporal object segmentation system determines a location of an object depicted in a video. In some cases, the temporal object segmentation system determines the object's location in a particular frame of the video based on information indicating a previous location of the object in a previous video frame. For example, an encoder neural network in the temporal object segmentation system extracts features describing image attributes of a video frame. A convolutional long-short term memory neural network determines the location of the object in the frame, based on the extracted image attributes and information indicating a previous location in a previous frame. A decoder neural network generates an image mask indicating the object's location in the frame. In some cases, a video editing system receives multiple generated masks for a video, and modifies one or more video frames based on the locations indicated by the masks.

US Patent:

20200349189, Nov 5, 2020

Filed:

Jul 15, 2020

Appl. No.:

16/929429

Inventors:

- San Jose CA, US
Zhe Lin - Fremont CA, US
Kalyan Krishna Sunkavalli - San Jose CA, US
Hengshuang Zhao - Hong Kong, CN
Brian Lynn Price - Pleasant Grove UT, US

Assignee:

Adobe Inc. - San Jose CA

International Classification:

G06F 16/58
G06N 3/08
G06F 16/51

Abstract:

Compositing aware digital image search techniques and systems are described that leverage machine learning. In one example, a compositing aware image search system employs a two-stream convolutional neural network (CNN) to jointly learn feature embeddings from foreground digital images that capture a foreground object and background digital images that capture a background scene. In order to train models of the convolutional neural networks, triplets of training digital images are used. Each triplet may include a positive foreground digital image and a positive background digital image taken from the same digital image. The triplet also contains a negative foreground or background digital image that is dissimilar to the positive foreground or background digital image that is also included as part of the triplet.