Jose L Echevarria

US Patent:

20220358280, Nov 10, 2022

Filed:

Sep 29, 2021

Appl. No.:

17/489474

Inventors:

- San Jose CA, US
Franck DERNONCOURT - San Jose CA, US
Jose Ignacio ECHEVARRIA VALLESPI - Belmont CA, US
Paul ASENTE - Redwood City CA, US
Nedim LIPKA - Campbell CA, US
Thamar I. SOLORIO MARTINEZ - Cypress TX, US

International Classification:

G06F 40/109
G06F 40/169
G06N 3/02

Abstract:

Embodiments are disclosed for recommending fonts based on text inputs are described. In some embodiments, a method of recommending fonts includes receiving a selection of text, providing a representation of the selection of text to a font recommendation model, generating, by the font recommendation model, a prediction score for each of a plurality of fonts based on the representation of the selection of text, and returning at least one recommended font based on the prediction score for each of the plurality of fonts.

US Patent:

20210342974, Nov 4, 2021

Filed:

Apr 29, 2020

Appl. No.:

16/861688

Inventors:

- San Jose CA, US
Zhifei Zhang - San Jose CA, US
Jose Ignacio Echevarria Vallespi - San Francisco CA, US
Zhaowen Wang - San Jose CA, US
Stephen Diverdi - Berkeley CA, US

International Classification:

G06T 3/40
G06N 20/00

Abstract:

Systems and methods for texture hallucination with a large upscaling factor are described. Embodiments of the systems and methods may receive an input image and a reference image, extract an upscaled feature map from the input image, match the input image to a portion of the reference image, wherein a resolution of the reference image is higher than a resolution of the input image, concatenate the upscaled feature map with a reference feature map corresponding to the portion of the reference image to produce a concatenated feature map, and generate a reconstructed image based on the concatenated feature map using a machine learning model trained with a texture loss and a degradation loss, wherein the texture loss is based on a high frequency band filter, and the degradation loss is based on a downscaled version of the reconstructed image.

US Patent:

20210133279, May 6, 2021

Filed:

Nov 4, 2019

Appl. No.:

16/672733

Inventors:

- San Jose CA, US
Franck Dernoncourt - Sunnyvale CA, US
Paul Asente - Redwood City CA, US
Nedim Lipka - Santa Clara CA, US
Seokhwan Kim - San Jose CA, US
Jose Echevarria - San Jose CA, US

International Classification:

G06F 17/24
G06N 3/04
G06F 17/27
G06N 5/04

Abstract:

The present disclosure relates to utilizing a neural network to flexibly generate label distributions for modifying a segment of text to emphasize one or more words that accurately communicate the meaning of the segment of text. For example, the disclosed systems can utilize a neural network having a long short-term memory neural network architecture to analyze a segment of text and generate a plurality of label distributions corresponding to the words included therein. The label distribution for a given word can include probabilities across a plurality of labels from a text emphasis labeling scheme where a given probability represents the degree to which the corresponding label describes the word. The disclosed systems can modify the segment of text to emphasize one or more of the included words based on the generated label distributions.

US Patent:

20200364914, Nov 19, 2020

Filed:

May 17, 2019

Appl. No.:

16/416123

Inventors:

- San Jose CA, US
Jose Ignacio Echevarria Vallespi - San Jose CA, US
Jingwan Lu - Santa Clara CA, US
Jianming Zhang - Campbell CA, US
Jane Little E - Redwood City CA, US

International Classification:

G06T 11/60
G06T 7/70
G06T 7/33
G06T 7/32
G06T 7/00

Abstract:

Various methods and systems are provided for image-management operations that includes generating adaptive image armatures based on an alignment between composition lines of a reference armature and a position of an object in an image. In operation, a reference armature for an image is accessed. The reference armature includes a plurality of composition lines that define a frame of reference for image composition. An alignment map is determined using the reference armature. The alignment map includes alignment information that indicates alignment between the composition lines of the reference armature and the position of the object in the image. Based on the alignment map, an adaptive image armature is determined. The adaptive image armature includes a subset of the composition lines of the reference armature. The adaptive image armature is displayed.

US Patent:

20200160567, May 21, 2020

Filed:

Nov 21, 2018

Appl. No.:

16/197633

Inventors:

- San Jose CA, US
Jose Ignacio Echevarria Vallespi - San Jose CA, US

International Classification:

G06T 11/00

Abstract:

In some embodiments, a computing system computes a palette-based color harmony and applies palette-based image recoloration by determining a color palette for the electronic image that includes a first image color at a first position on a color space and a second image color at a second position on a color space. The computing system applies a harmonic template using a combination of a global rotation angle and a secondary rotation angle, such that, the harmonic template, as applied, minimizes an aggregate of hue distances. The computing system modifies the color palette by moving at least one of (i) the first image color from the first position toward a position along a first axis of the harmonic template or (ii) the second image color from the second position toward a modified position along a second axis of the harmonic template. The computing system updates an editing interface.

US Patent:

20190340419, Nov 7, 2019

Filed:

May 3, 2018

Appl. No.:

15/970831

Inventors:

- San Jose CA, US
Jose Ignacio Echevarria Vallespi - San Jose CA, US
Jingwan Lu - Santa Clara CA, US
Elya Shechtman - Seattle WA, US
Duygu Ceylan Aksit - San Jose CA, US
David P. Simons - Seattle WA, US

Assignee:

Adobe Inc. - San Jose CA

International Classification:

G06K 9/00
G06T 13/40
G06T 19/00
G06F 15/18

Abstract:

Generation of parameterized avatars is described. An avatar generation system uses a trained machine-learning model to generate a parameterized avatar, from which digital visual content (e.g., images, videos, augmented and/or virtual reality (AR/VR) content) can be generated. The machine-learning model is trained to identify cartoon features of a particular style—from a library of these cartoon features—that correspond to features of a person depicted in a digital photograph. The parameterized avatar is data (e.g., a feature vector) that indicates the cartoon features identified from the library by the trained machine-learning model for the depicted person. This parameterization enables the avatar to be animated. The parameterization also enables the avatar generation system to generate avatars in non-photorealistic (relatively cartoony) styles such that, despite the style, the avatars preserve identities and expressions of persons depicted in input digital photographs.

US Patent:

20190295272, Sep 26, 2019

Filed:

Mar 22, 2018

Appl. No.:

15/928520

Inventors:

- San Jose CA, US
Zhili Chen - San Jose CA, US
Jose Ignacio Echevarria Vallespi - San Jose CA, US
Kyle Olszewski - Los Angeles CA, US

International Classification:

G06T 7/529
G06K 9/00
G06T 15/04

Abstract:

Certain embodiments involve synthesizing image content depicting facial hair or other hair features based on orientation data obtained using guidance inputs or other user-provided guidance data. For instance, a graphic manipulation application accesses guidance data identifying a desired hair feature and an appearance exemplar having image data with color information for the desired hair feature. The graphic manipulation application transforms the guidance data into an input orientation map. The graphic manipulation application matches the input orientation map to an exemplar orientation map having a higher resolution than the input orientation map. The graphic manipulation application generates the desired hair feature by applying the color information from the appearance exemplar to the exemplar orientation map. The graphic manipulation application outputs the desired hair feature at a presentation device.

US Patent:

20190272668, Sep 5, 2019

Filed:

Mar 5, 2018

Appl. No.:

15/912324

Inventors:

- San Jose CA, US
Jose Ignacio Echevarria Vallespi - San Jose CA, US

Assignee:

Adobe Inc. - San Jose CA

International Classification:

G06T 15/10
G06K 9/00
G06T 7/73
G06T 15/50

Abstract:

Caricature generation techniques and systems are described that are configured to preserve an individuality identity of a subject of the caricature and thus overcome inaccuracies and failures of conventional techniques. In one example, a caricature generation system is employed by a computing device to determine deviations of facial features of a subject captured by a digital image from reference values. Caricature-specific blend shapes are then employed by the caricature generation system to generate a digital image caricature from a digital image based on these deviations. In one example, blend shapes include interaction rules that define an interplay of distortions that are jointly applied to at least two of the facial features of a subject in the digital image.