Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing a critical edge detection neural network and a geometric model to determine camera parameters from a single digital image. In particular, in one or more embodiments, the disclosed systems can train and utilize a critical edge detection neural network to generate a vanishing edge map indicating vanishing lines from the digital image. The system can then utilize the vanishing edge map to more accurately and efficiently determine camera parameters by applying a geometric model to the vanishing edge map. Further, the system can generate ground truth vanishing line data from a set of training digital images for training the critical edge detection neural network.

Abstract: Embodiments of an expansion joint are provided. The expansion joint is configured to cover a gap between a first architectural surface and a second architectural surface. The expansion joint includes a panel having a first surface and a second surface in which the second surface is opposite the first surface. When the panel covers the gap, the panel is magnetically connected to both of the first architectural surface or the second architectural surface. In specific embodiments, at least one of the magnetic structures that magnetically connect the panel to both of the first architectural surface or the second architectural surface is allowed to move in response to movement of the panel. In more specific embodiments, the movement of the magnetic structure is a tilting movement.

Abstract: Aspects of the current disclosure include systems and methods for identifying an entity in a query image by comparing the query image with digital images in a database. In one or more embodiments, a query feature may be extracted from the query image and a set of candidate features may be extracted from a set of images in the database. In one or more embodiments, the distances between the query feature and the candidate features are calculated. A feature, which includes a set of shortest distances among the calculated distances and a distribution of the set of shortest distances, may be generated. In one or more embodiments, the feature is input to a trained model to determine whether the entity in the query image is the same entity associated with one of the set of shortest distances.

Abstract: Certain aspects involve video inpainting in which content is propagated from a user-provided reference frame to other video frames depicting a scene. For example, a computing system accesses a set of video frames with annotations identifying a target region to be modified. The computing system determines a motion of the target region's boundary across the set of video frames, and also interpolates pixel motion within the target region across the set of video frames. The computing system also inserts, responsive to user input, a reference frame into the set of video frames. The reference frame can include reference color data from a user-specified modification to the target region. The computing system can use the reference color data and the interpolated motion to update color data in the target region across set of video frames.

Abstract: Aspects of the current disclosure include systems and methods for identifying an entity in a query image by comparing the query image with digital images in a database. In one or more embodiments, a query feature may be extracted from the query image and a set of candidate features may be extracted from a set of images in the database. In one or more embodiments, the distances between the query feature and the candidate features are calculated. A feature, which includes a set of shortest distances among the calculated distances and a distribution of the set of shortest distances, may be generated. In one or more embodiments, the feature is input to a trained model to determine whether the entity in the query image is the same entity associated with one of the set of shortest distances.

Abstract: According to one example, an exercise system includes a vertical housing, a first weight system coupled to a first upper weighted touchpoint, a second weight system coupled to a second upper weighted touchpoint, a third weight system coupled to a first lower weighted touchpoint, and a fourth weight system coupled to a second lower weighted touchpoint. The exercise system further includes a control system that is configured to cause the first weight system to provide weight to the first upper weighted touchpoint independent of each of the second, third, and fourth weight systems, and cause the third weight system to provide weight to the first lower weighted touchpoint independent of each of the first, second, and fourth weight systems. The first upper weighted touchpoint and the first lower weighted touchpoint may allow the user to exercise the first arm and the first leg of the user simultaneously.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a multi-stroke neural network for modifying a digital image via a plurality of generated stroke parameters in a single pass of the neural network. Specifically, the disclosed system utilizes an encoder neural network to generate an encoding of a digital image. The disclosed system then utilizes a decoder neural network that generates a sequence of stroke parameters for digital drawing strokes from the encoding in a single pass of the encoder neural network and decoder neural network. Additionally, the disclosed system utilizes a renderer neural network to render the digital drawing strokes on a digital canvas according to the sequence of stroke parameters. In additional embodiments, the disclosed system utilizes a balance of loss functions to learn parameters of the multi-stroke neural network to generate stroke parameters according to various rendering styles.

Abstract: Techniques for generating a stylized drawing of three-dimensional (3D) shapes using neural networks are disclosed. A processing device generates a set of vector curve paths from a viewpoint of a 3D shape; extracts, using a first neural network of a plurality of neural networks of a machine learning model, surface geometry features of the 3D shape based on geometric properties of surface points of the 3D shape; determines, using a second neural network of the plurality of neural networks of the machine learning model, a set of at least one predicted stroke attribute based on the surface geometry features and a predetermined drawing style; generates, based on the at least one predicted stroke attribute, a set of vector stroke paths corresponding to the set of vector curve paths; and outputs a two-dimensional (2D) stylized stroke drawing of the 3D shape based at least on the set of vector stroke paths.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for accurately and flexibly generating scalable fonts utilizing multi-implicit neural font representations. For instance, the disclosed systems combine deep learning with differentiable rasterization to generate a multi-implicit neural font representation of a glyph. For example, the disclosed systems utilize an implicit differentiable font neural network to determine a font style code for an input glyph as well as distance values for locations of the glyph to be rendered based on a glyph label and the font style code. Further, the disclosed systems rasterize the distance values utilizing a differentiable rasterization model and combines the rasterized distance values to generate a permutation-invariant version of the glyph corresponding glyph set.

Abstract: According to one example, an exercise system includes a vertical housing, a first weighted touchpoint coupled to the vertical housing and configured to allow a user to exercise one or more muscles on a first side of the user, a first weight system coupled to the first weighted touchpoint, a second weighted touchpoint coupled to the vertical housing and configured to allow the user to exercise one or more muscles on a second side of the user, and a second weight system coupled to the second weighted touchpoint. The exercise system further includes a control system configured to cause the first weight system to automatically provide a first heavier weight to the first weighted touchpoint for a first exercise and further cause the second weight system to automatically provide a second lighter weight to the second weighted touchpoint for the first exercise.

Abstract: Techniques are described herein for generating and using a unified shape representation that encompasses features of different types of shape representations. In some embodiments, the unified shape representation is a unicode comprising a vector of embeddings and values for the embeddings. The embedding values are inferred, using a neural network that has been trained on different types of shape representations, based on a first representation of a three-dimensional (3D) shape. The first representation is received as input to the trained neural network and corresponds to a first type of shape representation. At least one embedding has a value dependent on a feature provided by a second type of shape representation and not provided by the first type of shape representation. The value of the at least one embedding is inferred based upon the first representation and in the absence of the second type of shape representation for the 3D shape.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating scalable and semantically editable font representations utilizing a machine learning approach. For example, the disclosed systems generate a font representation code from a glyph utilizing a particular neural network architecture. For example, the disclosed systems utilize a glyph appearance propagation model and perform an iterative process to generate a font representation code from an initial glyph. Additionally, using a glyph appearance propagation model, the disclosed systems automatically propagate the appearance of the initial glyph from the font representation code to generate additional glyphs corresponding to respective glyph labels. In some embodiments, the disclosed systems propagate edits or other changes in appearance of a glyph to other glyphs within a glyph set (e.g., to match the appearance of the edited glyph).

Abstract: A sputtering target comprising a target insert comprising a target metal compound and a skirt structure including a primary skirt and a secondary skirt. The primary skirt is disposed adjacent least a portion of a secondary skirt and comprises a first metal compound. The secondary skirt comprises a second metal compound that is different from the first metal compound.

Abstract: Embodiments are disclosed for generating multiple color theme variations from an input image using learned color distributions. A method of generating multiple color theme variations from an input image using learned color distributions includes obtaining, by a user interface manager, an input image, determining, by a color extraction manager, one or more color priors based on the input image, generating, by a color distribution modeling network, a plurality of color theme variations based on the one or more color priors, ranking, by a color theme evaluation network, the plurality of color theme variations, and generating, by a recolor manager, a plurality of recolored output images using the plurality of color theme variations.

Abstract: This disclosure involves applying an edit to objects in a vector design corresponding to a selected level of an object hierarchy. A system accesses a vector design comprising first, second, and third objects, each of the objects having a respective axis coordinate. The system assigns the first object and the second object to or within a common level in an object hierarchy based on determining that a similarity score comparing the two objects exceeds a threshold and that a modification causing the axis coordinates of the two objects to be adjacent maintains an overlap between the third object and the two objects. The system receives a user input selecting the first object and expands the selection to the second object based on the second object being assigned to the common level. The system applies an edit to the first and second objects based on the expansion of the selection.

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for determining a glyph and a font from a vector outline by applying various combinations of hash-based querying, path-descriptor matching, or anchor-point matching. For example, the disclosed systems can select a subset of candidate glyphs for a vector outline based on (i) comparing hash keys of candidate glyphs with a point-order-agnostic hash key corresponding to the vector outline and (ii) comparing a path descriptor for a primary path of the vector outline to path descriptors corresponding to candidate glyphs. By further comparing anchor points between the vector outline and the subset of candidate glyphs, the disclosed systems can select both a glyph and a font matching the vector outline.

Abstract: According to one example, an exercise system includes a vertical housing, a first weighted touchpoint coupled to the vertical housing and configured to allow a user to exercise one or more muscles on a first side of the user, a first weight system coupled to the first weighted touchpoint, a second weighted touchpoint coupled to the vertical housing and configured to allow the user to exercise one or more muscles on a second side of the user, and a second weight system coupled to the second weighted touchpoint. The exercise system further includes a control system configured to cause the first weight system to automatically provide a first heavier weight to the first weighted touchpoint for a first exercise and further cause the second weight system to automatically provide a second lighter weight to the second weighted touchpoint for the first exercise.

Abstract: An optical network component and method are herein described. The system and method include determining a first power of an optical modulator using a first photodetector and a second power of the transmitter using a second photodetector, determining a contrast ratio based on the first power and the second power, and determining a modulation loss based on the contrast ratio.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for generating a three-dimensional scene based on a natural language phrase. For example, the disclosed system can analyze a natural language phrase to determine dependencies involving entities and commands in the natural language phrase. The disclosed system can then use the dependencies to generate an entity-command representation of the natural language phrase. Additionally, the disclosed system can generate a semantic scene graph for the natural language phrase from the entity-command representation to indicate contextual relationships of the entities and commands. Furthermore, the disclosed system generates the requested three-dimensional scene by using at least one scene of a plurality of available three-dimensional scenes identified using the semantic scene graph of the natural language phrase.

Abstract: Certain embodiments involve techniques for generating a 3D representation based on a provided 2D image of an object. An image generation system receives the 2D image representation and generates a multi-dimensional vector of the input that represents the image. The image generation system samples a set of points and provides the set of points and the multi-dimensional vector to a neural network that was trained to predict a 3D surface representing the image such that the 3D surface is consistent with a 3D surface of the object calculated using an implicit function for representing the image. The neural network predicts, based on the multi-dimensional vector and the set of points, the 3D surface representing the object.