Abstract: Computer-implemented methods for forming a training dataset for a machine learning model are described. The methods include receiving an intent object and two or more design snapshots associated with the intent object, where the intent object indicates an intended design outcome and the two or more design snapshots include at least a first design snapshot indicating an initial state of a design and a second design snapshot indicating a state of the design after the intended design outcome is achieved. One or more design edits made to the design based on the first design snapshot and the second design snapshot are identified. And a training datapoint based on the intent object and the identified one or more design edits is generated.

Abstract: Described herein is a computer implemented method for adjusting an image. The method includes displaying a first adjustment interface that includes including a first adjustment path and a first control for adjusting a first image processing parameter. The first adjustment path is displayed with a first gradient that is determined based on a first value of a second image processing parameter. The method further includes detecting a parameter adjustment that adjusts the first value of the second image processing parameter to a second value of the second image processing parameter and, in response to detecting the parameter adjustment: adjusting the image according to the second value of the second image processing parameter; determining a second gradient for the first adjustment path based on the second value of the second image processing parameter; and updating the first adjustment path to be displayed with the second gradient.

Abstract: Described herein is a computer implemented method for compressing a shape. The method includes: receiving input shape data defining first and second original shape commands and generating first and second compressed shape commands corresponding thereto. Generating the second compressed shape command includes generating a relative shape command that is a version of the second original shape command in which parameters are relatively defined; generating an absolute shape command that is a version of the second original shape command in which parameters are absolutely defined; and selecting a smaller or equal smallest of the relative shape command and the absolute shape command to be the second compressed shape command.

Abstract: Described herein is a computer implemented method for automatically generating a cropped version of an input image. The method includes processing the input image to detect a salient region of the input image and generating a set of crop candidates based on the salient region of the input image, each crop candidate defining a different image crop. A set of candidate scores is calculated, each corresponding to a crop candidate, and a first crop candidate is selected based on the set of scores. The cropped version of the input image is then generated based on the image crop defined by the first crop candidate.

Abstract: Described herein is a computer implemented method for compressing a shape. The method includes: receiving input shape data defining first and second original shape commands and generating first and second compressed shape commands corresponding thereto. Generating the second compressed shape command includes generating a relative shape command that is a version of the second original shape command in which parameters are relatively defined; generating an absolute shape command that is a version of the second original shape command in which parameters are absolutely defined; and selecting a smaller or equal smallest of the relative shape command and the absolute shape command to be the second compressed shape command.

Abstract: Described herein is a computer implemented method. The method includes receiving, via an input device, first user input drawing an input shape and generating, based on the first user input, original drawing data that includes an ordered set of points that define the input shape. The original drawing is processed to generate an input vector which also includes an ordered set of points. The input shape is then classified as a first template shape by processing the input vector using a machine learning model. A new shape is then generated based on the first template shape and the original drawing data.

Abstract: Described herein is a computer implemented method for adjusting an image. The method includes displaying a first adjustment interface that includes including a first adjustment path and a first control for adjusting a first image processing parameter. The first adjustment path is displayed with a first gradient that is determined based on a first value of a second image processing parameter. The method further includes detecting a parameter adjustment that adjusts the first value of the second image processing parameter to a second value of the second image processing parameter and, in response to detecting the parameter adjustment: adjusting the image according to the second value of the second image processing parameter; determining a second gradient for the first adjustment path based on the second value of the second image processing parameter; and updating the first adjustment path to be displayed with the second gradient.

Abstract: Computer processing systems and computer implemented methods for determining an arrangement of elements of a design are described. The arrangement may be into rows or columns. Collections of elements for rows and/or columns are determined based on overlap of the elements along a dimension prior to arrangement. Each collection may be arranged within an area of the design into a row or column. In some embodiments an initial arrangement into both rows and columns is determined and a final arrangement is determined based on which arrangement results in a least total overlap area of the elements.

Abstract: An apparatus includes an input interface, a processor, and a transmitter. The input interface is configured to receive user input associated with a design and to receive a user request indicating a selection of a website type of a plurality of website types. The processor is configured to update the design based on the user input. The updated design includes one or more design pages. The processor is configured to select, based on the website type, a specific set of website generation tasks. The processor is configured to perform the specific set of website generation tasks to generate one or more webpages of a website of the website type. The webpages correspond to the design pages. The transmitter is configured to send a web output to at least one of a data storage device, a publishing endpoint, or a client device. The web output corresponds to the webpages.

Abstract: Described herein is a computer implemented method for automatically generating a design. The method includes receiving an input prompt for generating the design and generating a design outline based on the input prompt. The design outline includes a style descriptor for the design. The method further includes retrieving a design template based on the design outline. The design template includes a placeholder design element. The method further includes retrieving at least one design element for the placeholder element. The design is generated by populating the placeholder element with the design element.

Abstract: Described herein is a computer implemented method including: retrieving historical search data including a plurality of historical search queries corresponding to historical searches for content items provided by a content delivery platform; processing the historical search data to determine a plurality of search topics, each search topic corresponding to a group of semantically similar historical search queries. The method further includes performing a first search for content items provided by the content delivery platform that are relevant to the first search topic and determining, based on results of the first search, a first content score that provides a measure of how much content provided by the content delivery platform is relevant to the first search topic and determining, based on the first content score, whether a content gap exists for the first search topic. In response determining that the content gap exists, a first content gap alert is generated.

Abstract: Described embodiments generally relate to a method of generating an image editing tool recommendation. The method includes receiving a prompt entered by a user; processing the prompt using a tool class prediction model to predict a tool class associated with the prompt, wherein the tool class is associated with at least one image editing tool that is configured to perform an image editing function described by the prompt; determining an image editing tool associated with the predicted tool class; and outputting a recommendation to the user directing the user to the determined image editing tool.

Abstract: Some embodiments relate to a method of performing prompt-based image editing. The method includes accessing an image; receiving a selected area of the image; receiving a prompt, wherein the prompt is indicative of an editing instruction; generating a latent by transforming the image into visual noise; predicting, based on the latent and the prompt, a noise image corresponding to the latent; subtracting at least a portion of the noise image from the latent to generate an updated latent; generating a noisy representation of the image; generating a masked latent based on the noisy representation, the updated latent and selected area, wherein the masked latent comprises the updated latent in the areas corresponding to the selected area, and the noisy representation in the areas that do not correspond to the selected area.

Abstract: Described herein is a computer implemented method for recolouring a vector graphic. Dominant colours defined by the vector graphic are determined, and a set of file colour groups is generated by associating file colours with dominant colours defined by the vector graphic. Colour change input data defining a particular file colour group and a new colour is received, and in response a colour transformation is determined. Corresponding transformed file colours are then calculated using the colour transformation.

Abstract: An apparatus includes a processor configured to receive, during editing of a first design, user input indicating that a first design element has a first content role. The processor is configured to generate a content signature of the first design indicating that the first design element has the first content role, to generate a second design based on a design template, and to update the second design by applying the content signature to the second design. Generating the second design includes, based on determining that the design template includes a second design element having the first content role, adding a third design element having the first content role to the second design. Applying the content signature to the second design includes transferring content from the first design element to the third design element. The processor is configured to generate a graphical user interface including an image of the second design.

Abstract: Described herein is a computer implemented method for compressing a shape. The method includes: receiving input shape data defining first and second original shape commands and generating first and second compressed shape commands corresponding thereto. Generating the second compressed shape command includes generating a relative shape command that is a version of the second original shape command in which parameters are relatively defined; generating an absolute shape command that is a version of the second original shape command in which parameters are absolutely defined; and selecting a smaller or equal smallest of the relative shape command and the absolute shape command to be the second compressed shape command.

Abstract: Described herein is a computer implemented method. The method includes accessing input image data defining a plurality of input pixels and processing the input image data to generate output image data. The output image data defines a plurality of output pixels, each corresponding to an input pixel. At least one output pixel is generated by a sampling process that includes: selecting a working pixel from the plurality of input pixels; selecting a set of sample pixels for the working pixel, wherein each sample pixel is an input pixel that is selected as a sample pixel based on whether the input pixel is positioned within a depth-adjusted sampling area, the depth-adjusted sampling area for a particular input pixel being determined based on a depth separation between that particular input pixel and the working pixel; and generating an output pixel corresponding to the working pixel based on the set of sample pixels.

Abstract: Described herein is a computer implemented method. The method includes a client application generating a document request and communicating the document request to a server system. The client application receives: document data including page data in respect of a plurality of pages of the document; recorded interaction data defining one or more interactive events that occurred during a recording of a presentation associated with the document; and media data including audio and/or video data recorded during the recording of the presentation. The client application replays the presentation by using the recorded interaction data to synchronise display of the pages with playback of the media data.

Abstract: Methods of training a machine learning model for image processing are described, as well as methods for image processing to determine a predicted rotation value for an image based on the trained machine learning model. A method of training includes utilising as a learning objective a reduction or minimisation of a classification loss. Training image pairs may be associated with classifications corresponding to rotation values for the purpose of determining the classification loss. An image may be divided into a plurality of images for determining an input to the machine learning model, for training or for image processing.

Abstract: Described herein is a computer implemented method. The method includes retrieving original drawing data that includes an ordered set of original drawing points that define an input shape, the original drawing data being associated with a first template shape type. The method further includes generating a plurality of synthetic shapes. Each synthetic shape is defined by an ordered set of synthetic shape points, and generating a particular synthetic shape includes performing a first operation that is based on the original drawing data. For each synthetic shape a training example is generated that includes the synthetic shape and is associated with the first template shape type.