Abstract: Font replacement based on visual similarity is described. In one or more embodiments, a font descriptor includes multiple font features derived from a visual appearance of a font by a font visual similarity model. The font visual similarity model can be trained using a machine learning system that recognizes similarity between visual appearances of two different fonts. A source computing device embeds a font descriptor in a document, which is transmitted to a destination computing device. The destination compares the embedded font descriptor to font descriptors corresponding to local fonts. Based on distances between the embedded and the local font descriptors, at least one matching font descriptor is determined. The local font corresponding to the matching font descriptor is deemed similar to the original font. The destination computing device controls presentations of the document using the similar local font. Computation of font descriptors can be outsourced to a remote location.

Abstract: Attribute control for updating digital content in a digital medium environment is described. The digital content is updated by incorporating new digital content components from a service provider system, such as a stock content service, to keep the digital content from seeming stale to client device users. The service provider system controls provision of digital content components based on fixed and variable attributes specified for these digital content components. Initially, the service provider system receives a component request, requesting that the service provider system provide the digital content components for incorporation with the digital content. The component request specifies fixed and variable content attributes for the provided digital content components. A fixed content attribute is an attribute that is to be included in the provided digital content components.

Abstract: An update basis for updating digital content in a digital medium environment is described. The digital content is updated by incorporating new digital content components from a service provider system, such as a stock content service, to keep the digital content from seeming stale to client device users. The service provider system controls provision of digital content components according to an update basis described in a component request. In part, component requests ask that the service provider system provide digital content components for incorporation with digital content. Component requests also describe a timing basis with which digital content components are to be provided as updates. By way of example, the timing basis may correspond to a time interval (e.g., daily, weekly, monthly, seasonally, times of day, and so on), receiving user input in relation to the digital content (e.g., a navigation input to a web page), and so forth.

Abstract: Embodiments provide traceability of edits to a document, i.e., a verifiable and immutable provenance chain for the document. In particular, embodiments facilitate providing analytics services for a distributed ledger. In implementation, a unique identifier associated with a digital document can be received from a remote computing device. Based on the received unique identifier, it is determined that the distributed ledger includes a first transaction corresponding to a first transitioned state of the digital document and a second transaction corresponding to a second transitioned state of the digital document. Each transaction includes the unique identifier, a first fingerprint of the digital document generated at a first time of a transitioned state, and a second fingerprint of the digital document generated at a second time of a previously transitioned state.

Abstract: Embodiments provide traceability of edits to a document, i.e., a verifiable and immutable provenance chain for the document. Systems and methods enable traceability of edits, by encoding, for states of the document, a fingerprint (e.g., a cryptographic hash of the document's contents) and an edit history within a block written to a distributed ledger (e.g., a blockchain). The ledger is maintained via a self-organizing peer-to-peer distributed ledger network. Once added to the ledger, the contents of a block (e.g., the document's fingerprint and edit history) are immutable and the integrity of the edit history encoded in the ledger is secure. The algorithm that generates the fingerprint is sensitive to edits of the document. The non-corruptible fingerprint encoded in the ledger is employable to detect any edits that are not included in the encoded edit history and/or inconsistent with a currently available version of the document.

Abstract: An update basis for updating digital content in a digital medium environment is described. The digital content is updated by incorporating new digital content components from a service provider system, such as a stock content service, to keep the digital content from seeming stale to client device users. The service provider system controls provision of digital content components according to an update basis described in a component request. In part, component requests ask that the service provider system provide digital content components for incorporation with digital content. Component requests also describe a timing basis with which digital content components are to be provided as updates. By way of example, the timing basis may correspond to a time interval (e.g., daily, weekly, monthly, seasonally, times of day, and so on), receiving user input in relation to the digital content (e.g., a navigation input to a web page), and so forth.

Abstract: In embodiments of event image curation, a computing device includes memory that stores a collection of digital images associated with a type of event, such as a digital photo album of digital photos associated with the event, or a video of image frames and the video is associated with the event. A curation application implements a convolutional neural network, which receives the digital images and a designation of the type of event. The convolutional neural network can then determine an importance rating of each digital image within the collection of the digital images based on the type of the event. The importance rating of a digital image is representative of an importance of the digital image to a person in context of the type of the event. The convolutional neural network generates an output of representative digital images from the collection based on the importance rating of each digital image.

Abstract: An intuitive object-generation experience is provided by employing an autoencoder neural network to reduce the dimensionality of a procedural model. A set of sample objects are generated using the procedural model. In embodiments, the sample objects may be selected according to visual features such that the sample objects are uniformly distributed in visual appearance. Both procedural model parameters and visual features from the sample objects are used to train an autoencoder neural network, which maps a small number of new parameters to the larger number of procedural model parameters of the original procedural model. A user interface may be provided that allows users to generate new objects by adjusting the new parameters of the trained autoencoder neural network, which outputs procedural model parameters. The output procedural model parameters may be provided to the procedural model to generate the new objects.

Abstract: An augmented reality (AR) mirror system is described. In an example, the AR mirror system includes a sensor, a display device, a semi-reflecting surface, a processing system, and computer-readable storage media having instructions stored thereon. The instructions are executable by the processing system to cause display of augmented reality (AR) digital content by the display device to be simultaneously viewable with a reflection of a physical object.

Abstract: Digital content interaction and navigation techniques and systems in virtual and augmented reality are described. In one example, techniques are employed to aid user interaction within a physical environment in which the user is disposed while viewing a virtual or augmented reality environment. In another example, techniques are described to support a world relative field of view and a fixed relative field of view. The world relative field of view is configured to follow motion of the user (e.g., movement of the user's head or mobile phone) within the environment to support navigation to different locations within the environment. The fixed relative field of view is configured to remain fixed during this navigation such that digital content disposed in this field of view remains at that relative location to a user's field of view.

Abstract: In embodiments of convolutional neural network joint training, a computing system memory maintains different data batches of multiple digital image items, where the digital image items of the different data batches have some common features. A convolutional neural network (CNN) receives input of the digital image items of the different data batches, and classifier layers of the CNN are trained to recognize the common features in the digital image items of the different data batches. The recognized common features are input to fully-connected layers of the CNN that distinguish between the recognized common features of the digital image items of the different data batches. A scoring difference is determined between item pairs of the digital image items in a particular one of the different data batches. A piecewise ranking loss algorithm maintains the scoring difference between the item pairs, and the scoring difference is used to train CNN regression functions.

Abstract: Font replacement based on visual similarity is described. In one or more embodiments, a font descriptor includes multiple font features derived from a visual appearance of a font by a font visual similarity model. The font visual similarity model can be trained using a machine learning system that recognizes similarity between visual appearances of two different fonts. A source computing device embeds a font descriptor in a document, which is transmitted to a destination computing device. The destination compares the embedded font descriptor to font descriptors corresponding to local fonts. Based on distances between the embedded and the local font descriptors, at least one matching font descriptor is determined. The local font corresponding to the matching font descriptor is deemed similar to the original font. The destination computing device controls presentations of the document using the similar local font. Computation of font descriptors can be outsourced to a remote location.

Abstract: A digital medium environment includes at least one computing device (e.g., a user's mobile device) in an environment. Systems and techniques are described for presenting a photorealistic augmented reality experience in real time on the computing device. A lighting representation of the environment is obtained from a partial view of the environment, such as from an image of the environment, and used to render a 3D asset (e.g., graphics of a synthetic object). The 3D asset is inserted into the environment by compositing the rendered 3D asset with the image of the environment accounting for occlusion and based on the lighting representation to form a composite image. Photorealistic processing is applied to the composite image by adding lighting for the rendered 3D asset to a portion of the background of the composite image. Consequently, the inserted graphic is indistinguishable from the real-world scene.

Abstract: Content creation and sharing integration techniques and systems are described. In one or more implementations, techniques are described in which modifiable versions of content (e.g., images) are created and shared via a content sharing service such that image creation functionality used to create the images is preserved to permit continued creation using this functionality. In one or more additional implementations, image creation functionality employed by a creative professional to create content is leveraged to locate similar images from a content sharing service.

Abstract: An augmented reality (AR) mirror system is described. In an example, the AR mirror system includes a sensor, a display device, a semi-reflecting surface, a processing system, and computer-readable storage media having instructions stored thereon. The instructions are executable by the processing system to cause display of augmented reality (AR) digital content by the display device to be simultaneously viewable with a reflection of a physical object.

Abstract: Font replacement based on visual similarity is described. In one or more embodiments, a font descriptor includes multiple font features derived from a visual appearance of a font by a font visual similarity model. The font visual similarity model can be trained using a machine learning system that recognizes similarity between visual appearances of two different fonts. A source computing device embeds a font descriptor in a document, which is transmitted to a destination computing device. The destination compares the embedded font descriptor to font descriptors corresponding to local fonts. Based on distances between the embedded and the local font descriptors, at least one matching font descriptor is determined. The local font corresponding to the matching font descriptor is deemed similar to the original font. The destination computing device controls presentations of the document using the similar local font. Computation of font descriptors can be outsourced to a remote location.

Abstract: This document describes techniques and apparatuses for 3D printing with small geometric offsets to affect surface characteristics. These techniques are capable of enabling fused-deposition printers to create 3D objects having desired surface characteristics, such as particular colors, images and image resolutions, textures, and luminosities. In some cases, the techniques do so using a single filament head with a single filament material. In some other cases, the techniques do so using multiple heads each with different filaments, though the techniques can forgo many switches between these heads. Each printing layer may use even a single filament from one head, thereby enabling surface characteristics while reducing starts and stops for filaments heads, which enables fewer artifacts or increases printing speed.

Abstract: Application personalization techniques and systems are described that leverage an embedded machine learning module to preserve a user's privacy while still supporting rich personalization with improved accuracy and efficiency of use of computational resources over conventional techniques and systems. The machine learning module, for instance, may be embedded as part of an application to execute within a context of the application to learn user preferences to train a model using machine learning. This model is then used within the context of execution of the application to personalize the application, such as control access to digital content, make recommendations, control which items of digital marketing content are exposed to a user via the application, and so on.

Abstract: Application personalization techniques and systems are described that leverage an embedded machine learning module to preserve a user's privacy while still supporting rich personalization with improved accuracy and efficiency of use of computational resources over conventional techniques and systems. The machine learning module, for instance, may be embedded as part of an application to execute within a context of the application to learn user preferences to train a model using machine learning. This model is then used within the context of execution of the application to personalize the application, such as control access to digital content, make recommendations, control which items of digital marketing content are exposed to a user via the application, and so on.

Abstract: Techniques and system are described to control output of digital marketing content with respect to a digital video that address the added complexities of digital video over other types of digital content, such as webpages. In one example, the techniques and systems are configured to control a time, at which, digital marketing content is to be output with respect to the digital video, e.g., by selecting a commercial break or output as a banner ad in conjunction with the video.