Abstract: A powder composition includes a plurality of thermoplastic particles and a plurality of flow promoting particles having an optimized flow, coalescence, or both; and methods of preparing three-dimensional articles and methods of preparing a powder coating, and articles prepared by the methods are described herein.

Abstract: Systems and techniques are described that provide for question answering using data visualizations, such as bar graphs. Such data visualizations are often generated from collected data, and provided within image files that illustrate the underlying data and relationships between data elements. The described techniques analyze a query and a related data visualization, and identify one or more spatial regions within the data visualization in which an answer to the query may be found.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing scale-diverse segmentation neural networks to analyze digital images at different scales and identify different target objects portrayed in the digital images. For example, in one or more embodiments, the disclosed systems analyze a digital image and corresponding user indicators (e.g., foreground indicators, background indicators, edge indicators, boundary region indicators, and/or voice indicators) at different scales utilizing a scale-diverse segmentation neural network. In particular, the disclosed systems can utilize the scale-diverse segmentation neural network to generate a plurality of semantically meaningful object segmentation outputs. Furthermore, the disclosed systems can provide the plurality of object segmentation outputs for display and selection to improve the efficiency and accuracy of identifying target objects and modifying the digital image.

Abstract: Provided are systems and methods for additive manufacturing, which systems and methods yield parts having improved interlayer adhesion. In the disclosed technology, additional heating steps are applied on the upper surface of the already printed workpiece so as to offset the dropping temperature of that surface during part fabrication. These heating steps elevate the temperature of the surface to a value that results in a molten interface with subsequently-applied build material, leading to improved interlayer adhesion. This technology is applicable to a variety of additive manufacturing processes, including but not limited to selective laser sintering, fused filament fabrication, and large format additive manufacturing approaches.

Abstract: A temporal object segmentation system determines a location of an object depicted in a video. In some cases, the temporal object segmentation system determines the object's location in a particular frame of the video based on information indicating a previous location of the object in a previous video frame. For example, an encoder neural network in the temporal object segmentation system extracts features describing image attributes of a video frame. A convolutional long-short term memory neural network determines the location of the object in the frame, based on the extracted image attributes and information indicating a previous location in a previous frame. A decoder neural network generates an image mask indicating the object's location in the frame. In some cases, a video editing system receives multiple generated masks for a video, and modifies one or more video frames based on the locations indicated by the masks.

Abstract: A particle separator is disclosed for a first fluid that includes solid particles of different sizes dispersed therein includes a flow path of the first fluid. A chamber is disposed below the first fluid flow path. The chamber includes an open upper portion adjacent to and below the first fluid flow path. A second fluid at a second density greater than the first density is disposed in the chamber. The second fluid is in contact with the first fluid flow path at the chamber open upper portion.

Abstract: A process for the manufacture of thermoplastic polymer particles in a yield of greater than 70% is described. The process includes dissolving a thermoplastic polymer in an organic solvent capable of dissolving the polymer to form a solution, emulsifying the solution by combining the solution with water and a surfactant to form an emulsion, removing the organic solvent to form a slurry, and recovering thermoplastic polymer particles having a diameter of less than 150 micrometers and in a yield of greater than 70%. The water is present in the emulsion in an amount of 5 to less than 50 weight percent. The thermoplastic polymer particles exhibit a combination of size characteristics. Thermoplastic polymer particles and articles prepared therefrom are also described.

Abstract: A forecasting neural network receives data and extracts features from the data. A recurrent neural network included in the forecasting neural network provides forecasted features based on the extracted features. In an embodiment, the forecasting neural network receives an image, and features of the image are extracted. The recurrent neural network forecasts features based on the extracted features, and pose is forecasted based on the forecasted features. Additionally or alternatively, additional poses are forecasted based on additional forecasted features.

Abstract: A powder composition including a plurality of thermoplastic particles having an optimized particle size and particle size distribution is disclosed. The powder composition includes a plurality of thermoplastic particles having a bimodal particle size distribution or a trimodal particle size distribution. Also disclosed are methods of preparing three-dimensional articles, methods of preparing a powder coating, and articles prepared by the methods.

Abstract: Certain aspects involve semantic segmentation of objects in a digital visual medium by determining a score for each pixel of the digital visual medium that is representative of a likelihood that each pixel corresponds to the objects associated with bounding boxes within the digital visual medium. An instance-level label that yields a label for each of the pixels of the digital visual medium corresponding to the objects is determined based, in part, on a collective probability map including the score for each pixel of the digital visual medium. In some aspects, the score for each pixel corresponding to each bounding box is determined by a prediction model trained by a neural network.

Abstract: Systems and methods are disclosed for selecting target objects within digital images utilizing a multi-modal object selection neural network trained to accommodate multiple input modalities. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators corresponding to various input modalities. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user inputs corresponding to different input modalities to select target objects in digital images. Specifically, the disclosed systems and methods can transform user inputs into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object.

Abstract: A method and system of scheduling a demand for a process inner loop are provided. The loop controller includes an inner loop control system configured to generate a control output signal for a controllable member and a schedule demand module configured to receive parameter values for a controlled variable of a process from a parameter source and to generate a scheduled demand output using a demand schedule. The loop controller also includes a schedule prediction module configured to predict a future value of a scheduling parameter based on a historical performance of the inner loop control system and current system dynamics and to generate a scheduled rate output. The schedule prediction module includes the rate-of-change of a scheduling parameter and a lead time input that defines a look-ahead time period used with the parameter rate signal to determine a future predicted value of the controlled variable.

Abstract: Systems and techniques are described that provide for question answering using data visualizations, such as bar graphs. Such data visualizations are often generated from collected data, and provided within image files that illustrate the underlying data and relationships between data elements. The described techniques analyze a query and a related data visualization, and identify one or more spatial regions within the data visualization in which an answer to the query may be found.

Abstract: Techniques for planar region-guided estimates of 3D geometry of objects depicted in a single 2D image. The techniques estimate regions of an image that are part of planar regions (i.e., flat surfaces) and use those planar region estimates to estimate the 3D geometry of the objects in the image. The planar regions and resulting 3D geometry are estimated using only a single 2D image of the objects. Training data from images of other objects is used to train a CNN with a model that is then used to make planar region estimates using a single 2D image. The planar region estimates, in one example, are based on estimates of planarity (surface plane information) and estimates of edges (depth discontinuities and edges between surface planes) that are estimated using models trained using images of other scenes.

Abstract: Systems and methods are disclosed for selecting target objects within digital images. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user indicators to select targeted objects in digital images. Specifically, the disclosed systems and methods can transform user indicators into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object.

Abstract: Systems and methods are disclosed for selecting target objects within digital images. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user indicators to select targeted objects in digital images. Specifically, the disclosed systems and methods can transform user indicators into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object.

Abstract: A method and system of scheduling a demand for a process inner loop are provided. The loop controller includes an inner loop control system configured to generate a control output signal for a controllable member and a schedule demand module configured to receive parameter values for a controlled variable of a process from a parameter source and to generate a scheduled demand output using a demand schedule. The loop controller also includes a schedule prediction module configured to predict a future value of a scheduling parameter based on a historical performance of the inner loop control system and current system dynamics and to generate a scheduled rate output. The schedule prediction module includes the rate-of-change of a scheduling parameter and a lead time input that defines a look-ahead time period used with the parameter rate signal to determine a future predicted value of the controlled variable.

Abstract: A forecasting neural network receives data and extracts features from the data. A recurrent neural network included in the forecasting neural network provides forecasted features based on the extracted features. In an embodiment, the forecasting neural network receives an image, and features of the image are extracted. The recurrent neural network forecasts features based on the extracted features, and pose is forecasted based on the forecasted features. Additionally or alternatively, additional poses are forecasted based on additional forecasted features.

Abstract: A forecasting neural network receives data and extracts features from the data. A recurrent neural network included in the forecasting neural network provides forecasted features based on the extracted features. In an embodiment, the forecasting neural network receives an image, and features of the image are extracted. The recurrent neural network forecasts features based on the extracted features, and pose is forecasted based on the forecasted features. Additionally or alternatively, additional poses are forecasted based on additional forecasted features.

Abstract: A forecasting neural network receives data and extracts features from the data. A recurrent neural network included in the forecasting neural network provides forecasted features based on the extracted features. In an embodiment, the forecasting neural network receives an image, and features of the image are extracted. The recurrent neural network forecasts features based on the extracted features, and pose is forecasted based on the forecasted features. Additionally or alternatively, additional poses are forecasted based on additional forecasted features.