Abstract: Embodiments are disclosed for articulated part extraction using images of animated characters from sprite sheets by a digital design system. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input including a plurality of images depicting an animated character in different poses. The disclosed systems and methods further comprise, for each pair of images in the plurality of images, determining, by a first machine learning model, pixel correspondences between pixels of the pair of images, and determining, by a second machine learning model, pixel clusters representing the animated character, each pixel cluster corresponding to a different structural segment of the animated character. The disclosed systems and methods further comprise selecting a subset of clusters that reconstructs the different poses of the animated character. The disclosed systems and methods further comprise creating a rigged animated character based on the selected subset of clusters.

Abstract: Compositions and coating mixtures for coating agricultural and other consumable products, and methods of preparing the compositions and coating mixtures.

Abstract: Embodiments are disclosed for articulated part extraction using images of animated characters from sprite sheets by a digital design system. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input including a plurality of images depicting an animated character in different poses. The disclosed systems and methods further comprise, for each pair of images in the plurality of images, determining, by a first machine learning model, pixel correspondences between pixels of the pair of images, and determining, by a second machine learning model, pixel clusters representing the animated character, each pixel cluster corresponding to a different structural segment of the animated character. The disclosed systems and methods further comprise selecting a subset of clusters that reconstructs the different poses of the animated character. The disclosed systems and methods further comprise creating a rigged animated character based on the selected subset of clusters.

Abstract: A visual lens system is described that identifies, automatically and without user intervention, digital tool parameters for achieving a visual appearance of an image region in raster image data. To do so, the visual lens system processes raster image data using a tool region detection network trained to output a mask indicating whether the digital tool is useable to achieve a visual appearance of each pixel in the raster image data. The mask is then processed by a tool parameter estimation network trained to generate a probability distribution indicating an estimation of discrete parameter configurations applicable to the digital tool to achieve the visual appearance. The visual lens system generates an image tool description for the parameter configuration and incorporates the image tool description into an interactive image for the raster image data. The image tool description enables transfer of the digital tool parameter configuration to different image data.

Abstract: Apparatuses, methods, and systems for generating signatures based on sensing one or more gas concentration conditions are disclosed. One method includes sensing, by one or more sensors, levels of a gas over time for a plurality of gas concentration conditions, receiving, by a controller, the sensed levels of gas over time for the plurality of gas concentration conditions, and generating, by the controller, a plurality of signatures, wherein one or more signatures is generated for one or more gas concentration conditions based on the sensed levels of gas over time, and determining whether to take action or not to take action.

Abstract: Apparatuses, methods, and systems for detecting a sample are disclosed. One method includes generating, by a tunable light source, a beam of electro-magnetic radiation, wherein a wavelength of the beam of electro-magnetic radiation is tuned to operate at a plurality of wavelengths. At least a portion of the beam of electro-magnetic radiation is directed to pass through the sample and a reference substance. The system detector is configured to sense at least the portion of the beam of electro-magnetic radiation after passing through the sample and the reference substance. The processor operates to receive information related to intensity or amplitude of the sensed beam of electro-magnetic radiation after passing through the sample and the reference substance and detect an amount of the sample based on the received information related to the intensity or amplitude of the sensed beam of the electro-magnetic radiation.

Abstract: Described herein are methods of preparing compounds derived from triglycerides or condensation polymers such as polyesters and/or polyamides. The methods may include subjecting triglyceride or condensation polymer containing matter to mechanical processing in the presence of a nucleophile.

Abstract: The present invention provides a method and system for controlling the temperature of an electric motor by adjusting the electric losses in the motor. In an embodiment, the required load on the motor is determined and a first motor voltage is provided to meet the required load. A predetermined temperature set point for the motor is compared against the temperature of the motor and based on the temperature of the motor and the predetermined temperature set point, a secondary motor voltage is determined. The motor voltage may then be adjusted based on the calculated voltage and the motor load measurement adjusted based on the measured motor speed and actual motor voltage.

Abstract: Semantic fill techniques are described that support generating fill and editing images from semantic inputs. A user input, for example, is received by a semantic fill system that indicates a selection of a first region of a digital image and a corresponding semantic label. The user input is utilized by the semantic fill system to generate a guidance attention map of the digital image. The semantic fill system leverages the guidance attention map to generate a sparse attention map of a second region of the digital image. A semantic fill of pixels is generated for the first region based on the semantic label and the sparse attention map. The edited digital image is displayed in a user interface.

Abstract: Apparatuses, methods, and systems for detecting a sample are disclosed. One method includes generating, by a tunable light source, a beam of electro-magnetic radiation, wherein a wavelength of the beam of electro-magnetic radiation is tuned to operate at a plurality of wavelengths. At least a portion of the beam of electro-magnetic radiation is directed to pass through the sample and a reference substance. The system detector is configured to sense at least the portion of the beam of electro-magnetic radiation after passing through the sample and the reference substance. The processor operates to receive information related to intensity or amplitude of the sensed beam of electro-magnetic radiation after passing through the sample and the reference substance and detect an amount of the sample based on the received information related to the intensity or amplitude of the sensed beam of the electro-magnetic radiation.

Abstract: Vector object transformation techniques are described that support generation of a transformed vector object based on a first vector object and a second vector object. A plurality of paths for a first and second vector object, for instance, are generated. Corresponding paths are determined by detecting which of the plurality of paths from the first vector object correspond to which of the plurality of paths from the second vector object. A mapping of control points between the first and second vector objects is generated. Using the mapping, a transformation of the first vector object is generated by adjusting one or more control points of the first vector object. As a result, the transformed vector object includes visual characteristics based on both the first vector object and the second vector object.

Abstract: Processes are described for obtaining highly purified tetrahydrocannabinolic acid (THCa) from Cannabis. Solvent extraction is performed on plant material or extract, followed by removal of impurities using sequential liquid-liquid extractions to purify cannabinoid carboxylic acids therefrom based on chemical properties of carboxylate salts. The product liquor, comprising THCa in solvent, is largely free of impurities, and high in THCa. Further steps can be conducted to obtain a highly enriched solution using chromatography and subsequent crystallization of THCa in 99% purity. THCa can be used as starting material for other products that include THC by decarboxylation. Optionally, triglyceride extraction of a washed aqueous phase can be used to prepare a THCa composition without chromatographic purification. A pre-processing aqueous extraction with pH manipulations may be used to remove biomass prior to solvent extraction, while maintaining THCa and optionally other cannabinoid acids.

Abstract: Vector object transformation techniques are described that support generation of a transformed vector object based on a first vector object and a second vector object. A plurality of paths for a first and second vector object, for instance, are generated. Corresponding paths are determined by detecting which of the plurality of paths from the first vector object correspond to which of the plurality of paths from the second vector object. A mapping of control points between the first and second vector objects is generated. Using the mapping, a transformation of the first vector object is generated by adjusting one or more control points of the first vector object. As a result, the transformed vector object includes visual characteristics based on both the first vector object and the second vector object.

Abstract: Embodiments are disclosed for reconstructing freeform gradients from an input image. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input image, computing an outline of the input image, identifying a set of candidate color handles for the input image, each candidate color handle of the set of candidate color handles representing an extremum point for a color in the input image, generating a reconstructed image using a subset of the set of candidate color handles, determining a reconstruction error by computing a difference between the input image and the reconstructed image, and providing the reconstructed image when the reconstruction error is below a threshold value.

Abstract: A computer-implemented method including receiving an input image at a first image stage and receiving a request to generate a plurality of variations of the input image at a second image stage. The method including generating, using an auto-regressive generative deep learning model, the plurality of variations of the input image at the second image stage and outputting the plurality of variations of the input image at the second image stage.

Abstract: A surgical tool for compact articulating during surgical procedures includes a pitch cable, at least one yaw cable, a first link, a second link, at least one end-effector link, and at least one tensioning mechanism. The first link has a pitch joint end with a pitch joint pin and at least one yaw cable guide channel. The second link has a yaw joint end with a yaw joint pin. The second link is rotatably connected to the pitch joint pin. The at least one end-effector link is rotatably connected to said yaw joint pin. The yaw cables are coupled to the end-effector links such that the yaw cables can actuate the end-effector links about the yaw joint pin. The yaw cable guide channel is configured such that the yaw cables travel through a smooth trajectory to the end-effector links. The tensioning mechanism is configured to maintain a constant length.

Abstract: Generating a vector representation of a hand-drawn sketch is described. To do so, the sketch is segmented into different superpixel regions. Superpixels are grown by distributing superpixel seeds throughout an image of the sketch and assigning unassigned pixels to a neighboring superpixel based on pixel value differences. The border between each pair of adjacent superpixels is then classified as either an active or an inactive boundary, with active boundaries indicating that the border corresponds to a salient sketch stroke. Vector paths are generated by traversing edges between pixel vertices along the active boundaries. To minimize vector paths included in the vector representation, vector paths are greedily generated first for longer curves along active boundaries until each edge is assigned to a vector path. Regions encompassed by vector paths corresponding to a foreground superpixel are filled to produce a high-fidelity vector representation of the sketch.

Abstract: Embodiments are disclosed for reconstructing freeform gradients from an input image. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input image, computing an outline of the input image, identifying a set of candidate color handles for the input image, each candidate color handle of the set of candidate color handles representing an extremum point for a color in the input image, generating a reconstructed image using a subset of the set of candidate color handles, determining a reconstruction error by computing a difference between the input image and the reconstructed image, and providing the reconstructed image when the reconstruction error is below a threshold value.

Abstract: A computer-implemented method including receiving an input image at a first image stage and receiving a request to generate a plurality of variations of the input image at a second image stage. The method including generating, using an auto-regressive generative deep learning model, the plurality of variations of the input image at the second image stage and outputting the plurality of variations of the input image at the second image stage.

Abstract: Vector object stylization techniques from raster objects are described that support editing of vector objects in a manner that maintains an underlying mathematical representation of object. A raster object, for instance, is generated from an edited version of an output of a vector object. This raster object, along with the vector object are received as inputs by a vector conversion system. These inputs are utilized by the vector conversion system to generate a stylized vector object having a visual appearance that mimics and simulates a visual appearance of the raster object. As a result, the stylized vector object provides a mathematical representation of the raster object.