Adobe, Inc.

Naveen Prakash Goel

Mayur Hemani

Harsh Vardhan Chopra

Amit Mittal

Abhishek Kumar

Vipul Aggarwal

Hemant Virmani

Kapil Arora

Nipun Poddar

Amit Gupta

Ashutosh Tripathi

Rekha Agarwal

Neha Rastogi

Himanshu Jindal

Sumeet Khurana

Sahil Gera

Shivang Mittal

Sachin Soni

Ramesh Srinivasaraghavan

Kazuhiro Toyoda

Abhishek Kumar Pandey

Siddharth Jain

Kedar Vijay Bodas

Michael Scrutton

Hemant Badhani

Lakshay Kumar

Sachin Beniwal

Gokul Krishna Paravasthu

Neha Pant

Anas Lnu

Shvet Chakra

Pratyush Kumar

Ardhendu Sekhar Panda

Ashish Chopra

Ritesh Agarwal

Sumeet Sahu

Pranjal Bhatnagar

Systems and methods dynamically generate tailored exit and post-exit content for web conferences. During presentation of conference content for a web conference, metadata is stored for one or more participant interactions with the web conference via a web conferencing client on a user device. Data associated with an exit from the web conference for the web conferencing client is received. Responsive to the data associated with the exit from the web conference, content is generated based on an exit context determined at least in part on the metadata regarding the one or more participant interactions. The generated content is provided for presentation on the user device.

Web conferencing exit and post-exit content generation

Methods and systems are provided for facilitating implementation of machine learning models in embedded software. In embodiments, a lean machine learning model, having a limited number of layers, is trained in association with a complex machine learning model, having a greater number of layers. To this end, a complex machine learning model, having a first number of layers, can be trained based on an output generated from a lean machine learning model used as input to the complex machine learning model. Further, the lean machine learning model, having a second number of layers less than the first number of layers, is trained using a loss value generated in association with training the complex machine learning model. Thereafter, the trained lean machine learning model can be provided for implementation in an embedded software.

Facilitating implementation of machine learning models in embedded software

Self-consumable portions generation techniques from a digital document are described. The self-consumable portions are generated based on a determination of an amount of resources available at a receiver device that is to receive the digital document. Examples of the resources include an amount of memory resources, processing resources, and/or network resources associated with the receiver device. The self-consumable portions, once generated, are separately renderable at the receiver device.

Self-consumable portion generation from a digital document

Spot aware print workflow techniques and system are described. In an implementation, a digital document is received for printing that includes a plurality of objects. Spot functionality is detected as corresponding to a respective object based on object properties detected for the respective object. One or more spot planes for are generated based on the spot functionality and a determination is made of color values for the one or more spot planes, respectively, based on context data describing a context, in which, the one or more spot planes are to be printed. The spot planes having the color values are output for printing by a print mechanism.

Automated content and context aware spot print workflow

The extraction of a three-dimensional (3D) object is facilitated using a printed hint, which includes an additional shape that is printed along with the 3D object in a granular-based printer bed. In example implementations, the hint is indicative of a location of the 3D object. In one example, a hint has a dimension indicative of a depth to the object in the printer bed. In another example, a position of a hint is indicative that the object is below, and a size of the hint is based on a size of the object. Some hints can also protect the object. Examples include plate and shell-shaped hints. The object is located under a plate hint or within a shell hint. Further, an appearance of the object or indications of the sturdiness of different parts of the object can be printed on the hint to facilitate a safe extraction of the object.

Facilitating extraction of three-dimensional object with printed hint

In implementations of pattern filling in garment pieces, a pattern filling system represents a first garment piece as a first curve and a second garment piece as a second curve. The system determines a relationship between the first garment piece and the second garment piece by comparing the first curve and the second curve. The pattern filling system generates a visually pleasing fill pattern for the first garment piece and the second garment piece based on the determined relationship.

Pattern filling in garment pieces

Techniques and systems are described for automatic artifact removal in a digital image. A segmentation map is generated that describes a magnitude of difference among pixels in a digital image. Contours may be generated that describe boundaries of objects described in the segmentation map. The contours may be filtered according to two-dimensional and three-dimensional cues to identify contours corresponding to artifacts in the digital image. For each contour corresponding to an artifact, an object mask and a sampling mask may be generated. The object mask and the sampling mask may be utilized as part of a content filling operation upon the digital image to remove the artifact, and a corrected digital image is generated that does not include the artifact.

Automatic artifact removal in a digital image

The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing intelligent sectioning and selective document reflow for section-based printing. For example, the disclosed systems can intelligently identify document objects (e.g., document structures and sections) within a digital document by utilizing a machine-learning model. In so doing, the disclosed systems can identify document-object types and document-object locations for the document objects in the digital document. In turn, the disclosed systems can provide, for display within a dynamic printing interface, selectable document sections comprising the identified document objects. In response to a user selection of one or more of the selectable document sections, the disclosed system can generate a modified digital document for printing by reflowing the identified document objects in accordance with the user selection. In some cases, reflowing comprises removing unselected document objects and/or repositioning one or more of the selected document objects.

Utilizing intelligent sectioning and selective document reflow for section-based printing

A method, apparatus, and non-transitory computer readable medium for color reduction based on image segmentation are described. The method, apparatus, and non-transitory computer readable medium may provide for segmenting an input image into a plurality of regions, assigning a weight to each region, identifying one or more colors for each of the regions, selecting a color palette based on the one or more colors for each of the regions and the corresponding weight for each of the regions, and performing a color reduction on the input image using the selected color palette to produce a color reduced image. The weight assigned to each region may depend on factors including relevance, prominence, focus, position, or any combination thereof.

Context aware color reduction

A computer implemented method and apparatus for preserving structural integrity of 3-D models when printing at varying scales, by use of a cueing model.

Method and apparatus for preserving structural integrity of 3-dimensional models when printing at varying scales

Techniques are described for obtaining at least one image using at least one processor. The techniques may include selecting a plurality of objects defined by a plurality of pixels within the at least one image. The techniques may include determining perceptual information associated with each of the plurality of objects and generating a context for each of the plurality of pixels that define the plurality of objects. The techniques may also include automatically thresholding the at least one image to generate an output image that represents the at least one image.

Content aware, spatially adaptive automated thresholding of images

Systems and methods are disclosed for generating viewpoints and/or digital images of defects in a three-dimensional model. In particular, in one or more embodiments, the disclosed systems and methods generate exterior viewpoints by clustering intersection points between a bounding sphere and rays originating from exterior vertices corresponding to one or more defects. In addition, in one or more embodiments, the disclosed systems and methods generate interior viewpoints by clustering intersection points between one or more medial spheres and rays originating from vertices corresponding to interior vertices corresponding to one or more defects. Furthermore, the disclosed systems and methods can apply colors to vertices corresponding to defects in the three-dimensional model such that adjacent vertices in the three-dimensional model have different colors and are more readily discernable.

Generating views of three-dimensional models illustrating defects

A computer implemented method and apparatus for embedding a 2D image in a 3D model. The method comprises generating a 3-dimensional (3D) print matrix representing a 2-dimensional (2D) image, wherein the print matrix comprises a plurality of sub-regions, the base plane of each sub-region angled with respect to a top surface of the print matrix so as to produce a plurality of shades, each shade representing a shade of the 2D image; and embedding the print matrix in a (3D) model.

Method and apparatus for embedding a 2-dimensional image in a 3-dimensional model

Local color information in a 3D mesh is used to enhance fine geometric features such as those in embroidered clothes for 3D printing. In some implementations, vertex color information is used to detect edges and to enhance geometry. In one embodiment, a 3D model is projected into a 2D space to obtain a 2D image, so that pixels that lie on edges in the 2D image can be detected. Further, such edge information is propagated back to the 3D model to enhance the geometry of the 3D model. Other embodiments may be described and/or claimed.

Growing community of inventors

Noida, India

Naveen Prakash Goel