Abstract: Techniques and systems for explanations of database query results by a virtual assistant are described. In an example, a processing device is operable to receive an input that includes a request in a natural language format related to a database. For example, the request is an instruction to create, alter, retrieve, delete, manage, or manipulate the database or data in the database. A first machine-learning model (e.g., a large language model (LLM)) generates a database query based on the request. The processing device queries the database using the database query to obtain a query result. A second machine-learning model generates a query explanation of the database query in the natural language format. The processing device then presents the query result and query explanation in a user interface.

Abstract: Techniques related to material glint generation for digital content are described. In an example, a processing device is operable to output a user interface that previews an object model and receive a material selection that designates a material part of the object model. The processing device is further operable to obtain a plurality of sample images showing different views of the object model and the material part designated by the material selection, input the sample images and the material selection into a material selector model that creates a similarity point cloud enabling material similarity querying across multiple material parts of the object model, and presents, via the user interface, an indication of different material parts of the object model that have a similar material as the material part designated by the material selection.

Abstract: A topic mapping system generates customized mapping schemas for multiple topic sets. The topic mapping system generates document clusters that represent groups of digital documents. The topic mapping system also generates, for each topic set, a document-topic mapping data object (“DTM data object”) that describes a customized mapping schema of the document clusters to labels in the topic set. The topic mapping system identifies customized groups of documents for responding to multiple requests that have a particular keyword. For each request, the topic mapping system identifies a particular topic set and DTM data object associated with a computing system that provided the request. Based on the keyword, the topic mapping system identifies documents that are categorized according to the customized mapping schema in the DTM data object. The topic mapping system can provide customized groups of documents to respective computing systems that provided the multiple requests.

Abstract: Systems and methods are disclosed herein for determining user segments created by a predictive model based on user behavioral data. A data analysis application executing on a computing device receives training data and a user input defining an outcome of interest. The data analysis application trains a predictive model with the training data and the outcome of interest. The data analysis application generates input data for each of a set of conditions determined from the training data. The data analysis application receives predicted outcome from the predictive model based on the input data. The data analysis application determines the relevance of the condition based on a comparison of the predicted outcome and the outcome of interest. The data analysis application generates a user segment that comprises a condition from the set of conditions based on the relevance of the condition.

Abstract: A system accesses, during a camera scan of a 3D physical object, video feed data of a user computing device including a plurality of frames. The system generates camera scan data including a set of 2D images of the physical object generated from a subset of the plurality of frames. Generating the camera scan data can include, responsive to determining that a translation between a previous frame and a current frame is greater than a threshold, including the current frame in the camera scan data. Generating the camera scan data can include excluding the current frame from the camera scan data responsive to determining an undesired camera movement type associated with the current frame. Generating the camera scan data can include indicating, in a surface coverage preview model, points of the 3D physical object included in at least a predefined number of consecutive frames of the subset of frames.

Abstract: Methods, computer systems, computer-storage media, and graphical user interfaces are provided for automated propagation of glyph edits to corresponding adornments. In embodiments, an indication to attach an adornment to a glyph associated with a variable font is identified. Thereafter, an anchor point indicating a point of attachment of the adornment to the glyph is identified. Based on obtaining an indication to modify a variable font property associated with the glyph, an edit to apply to the adornment is determined. Generally, the edit maintains an alignment of the adornment with a modified anchor point reflecting the modified variable font property associated with the glyph. Thereafter, the edit is applied to the adornment.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for generating segmentations of a raster image via a half-edge mesh structure with scanline operations. The disclosed system determines, during scanline operations on a raster image, a plurality of sets of adjacent pixels having a common color value in the raster image. The disclosed system determines, during the scanline operations on the raster image, a plurality of half-edges at edges of pixels along a boundary of a set of adjacent pixels of the plurality of sets of adjacent pixels with next half-edge directions indicating directions of subsequent half-edges along the boundary of the set of adjacent pixels. The disclosed system generates one or more oriented polyline boundary loops representing the boundary of the set of adjacent pixels from the plurality of half-edges and the next half-edge directions of the set of adjacent pixels.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for editing shadows in digital images. In particular, in some embodiments, the disclosed systems determine, utilizing a lighting estimation network, an environment map for a digital image, the environment map comprising a dominant light. In addition, in some embodiments, the disclosed systems generate, utilizing a lighting diffusion network, a diffused image from the digital image, the diffused image comprising smoothed shading. Moreover, in some embodiments, the disclosed systems generate, utilizing a shadow synthesis network, a shadowed image from the diffused image and a modified environment map comprising a modified dominant light. Furthermore, in some embodiments, the disclosed systems generate, from the diffused image and the shadowed image, a modified digital image comprising an edited shadow.

Abstract: A query system is described that supports retriever machine-learning model training data generation and implementation. The retriever machine-learning model is configured to retrieve examples for inclusion in a prompt formed from an input query that provide context for the query in performance of a corresponding task. The query system, in one or more examples, implements an alternating minimization technique for example selection that enhances in-context learning (ICL) performance for resources having few initial examples, e.g., for an initial resource. The query system is also configurable to incorporate example diversity that improves generalization and reduces bias in the retriever machine-learning model used to select the examples.

Abstract: Embodiments are disclosed for a precise book page boundary detection using deep machine learning model and image processing. The method may include generating, based on inputting a digital image to a convolutional neural segmentation network, a plurality of outputs comprising first output for a boundary of a left page of a spread of a physical book and second output for a boundary of a right page of the spread. A first thin pixel mask and a second thin pixel mask are determined for the left page and the right page based on the first and second outputs. A first quadrilateral and a second quadrilateral are determined based on the first and second thin pixel masks. At least one of the first or second quadrilateral is rendered in a display showing the outer boundary of the left or right page.

Abstract: Techniques and systems are provided for glyph-aware text selection. For instance, a glyph selection system can detect that a user has selected a glyph within a user interface. The glyph selection system can highlight the glyph and/or a region encompassing the glyph to communicate, to the user, that the glyph is selected. This highlighted region can be determined based on the shape and/or outline of the glyph. For example, the glyph selection system can determine bounds (e.g. coordinates) of the glyph in order to highlight a region within the user interface that fully encompasses the glyph and does not include portions of unselected glyphs. In some cases, the highlighted region may be rectangular. Alternatively, the highlighted region may be non-rectangular, such as a border defined by the outline of the glyph.

Abstract: In implementations of systems for generating digital content, a computing device implements a generation system to receive a user input specifying a characteristic for digital content. The generation system generates input text based on the characteristic for processing by a first machine learning model. Output text generated by the first machine learning model based on processing the input text is received. The output text describes a digital content component. The generation system generates the digital content component by processing the output text using a second machine learning model. The generation system generates the digital content including the digital content component for display in a user interface based on the characteristic.

Abstract: Embodiments are disclosed for an audio recommendation system trained to recommend music audio sequences for pairing with query video sequences using neural networks. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input including a query video sequence and natural language text. The disclosed systems and methods further comprise generating a fused visual-text embedding based on a visual embedding and a text embedding corresponding to the input. The disclosed systems and methods further comprise comparing audio embeddings for music audio sequences of a music audio sequences database with the fused visual-text embedding. The disclosed systems and methods further comprise determining a music audio sequence from the music audio sequences database as the recommended music audio sequence for pairing with the query video sequence based on a similarity metric calculated between an audio embedding for the music audio sequence and the fused visual-text embedding.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating derived dimensions within ingested data collections. In particular, in one or more embodiments, the disclosed systems generate derived dimensions that modify or correct one or more organizational schemas of an ingested data collection when querying the ingested data collection. For example, the disclosed systems receive a user-defined definition, and generates a fallback expression based on the user-defined definition and aligned to the schema of a particular ingested data collection. In at least one embodiment, the disclosed systems generate the derived dimension by identifying and modifying one or more existing dimensions in the schema based on the fallback expression when reading data from the ingested data collection.

Abstract: Context-based prompt generation techniques for generative machine-learning models are described. In one or more examples, a user interface (UI) selection of a UI element of first digital content is received. A processing device captures contextual information associated with the UI selection. A machine-learning model generates a prompt based on the UI selection and the contextual information. Generative artificial intelligence (AI) generates second digital content based on the prompt. The generative AI is implemented using one or more machine-learning models. The processing device then presents the second digital content for display in a user interface.

Abstract: Techniques for volumetric re-lighting of 3D objects are disclosed. In an example method, a computing system receives a first image of a three-dimensional (“3D”) object. The computing system generates a de-lighted image of the 3D object based on the first image. The computing system generates an embedded representation of the 3D object based on the de-lighted image and a first representation of the de-lighted image based on the embedded representation using a first machine learning (“ML”) model. The computing system generates a second representation of the 3D object using a second ML model based on orientation and lighting information and one or more internal states of the first ML model. The computing system generates a third representation of the 3D object by combining the first and second representations. The computing system renders a second image of the 3D object based on the third representation of the 3D object.

Abstract: Embodiments are disclosed for a method including obtaining a region of interest of a current frame of a video sequence depicting an object. The method may further include determining, by a mask propagation model, a likelihood of each pixel of the current frame being associated with the object in the region of interest of the current frame based on the region of interest of the current frame and a fixed number of previous frames of the video sequence including the object. The method may further include replacing a previous frame of the fixed number of previous frames with the current frame. The method may further include displaying the current frame of the video sequence including a masked object in the region of interest of the current frame based on the likelihood of one or more pixels of the current frame being associated with the object.

Abstract: Embodiments are disclosed for multi-color light-diffuser devices capable of displaying different colors based on stack configurations of polymer dispersed liquid crystal (PDLC) diffuser components, base layers, and filter layers. In one embodiment, a multi-color light-diffuser device can include a base layer positioned underneath a filter layer and a PDLC diffuser component positioned above the filter layer. In another embodiment, a multi-color light-diffuser can include an additional PDLC diffuser component in between the base layer and filter layer. The filter layer can be a dichroic material, a neutral density filter, or other transparent or semi-transparent material. The base layer can be an opaque material, such as paper, holographic film, iridescent film, or a mirror.

Abstract: Machine-learning prompt enhancement techniques are described. In one or more examples, by generating training data from high-quality digital content meeting specific criteria, a generative artificial intelligence (AI) system is configurable to train an enhancement machine-learning model to capture features pertaining to particular tasks or scenarios. The trained enhancement machine-learning model can then extract enhancement features from inputs, enabling the formation of enhanced prompts that guide generative AI models to generate digital content as suitable for the particular tasks or scenarios.