Abstract: One embodiment of the present invention sets forth a technique for performing frame interpolation. The technique includes generating (i) a first set of feature maps based on a first set of rendering features associated with a first key frame, (ii) a second set of feature maps based on a second set of rendering features associated with a second key frame, and (iii) a third set of feature maps based on a third set of rendering features associated with a target frame. The technique also includes applying one or more neural networks to the first, second, and third set of feature maps to generate a set of mappings from a first set of pixels in the first key frame to a second set of pixels in the target frame. The technique further includes generating the target frame based on the set of mappings.

Abstract: Techniques for aligning object representations for animation include analyzing a source object representation and a target object representation to identify a category of the source object and a category of the target object. Based on the category or categories of the objects, a feature extraction machine learning models is selected. The source object representation and the target object representation are provided as input to the selected feature extraction machine learning model to generate respective semantic descriptors and shape vectors for the source and target objects. Based on the semantic descriptors and the shape vectors for the source and target objects, an alignment machine learning model generates an aligned target object representation that is aligned with the source object representation and usable for animating the target object.

Abstract: A modular architecture is provided for denoising Monte Carlo renderings using neural networks. The temporal approach extracts and combines feature representations from neighboring frames rather than building a temporal context using recurrent connections. A multiscale architecture includes separate single-frame or temporal denoising modules for individual scales, and one or more scale compositor neural networks configured to adaptively blend individual scales. An error-predicting module is configured to produce adaptive sampling maps for a renderer to achieve more uniform residual noise distribution. An asymmetric loss function may be used for training the neural networks, which can provide control over the variance-bias trade-off during denoising.

Abstract: A system includes a processor and a memory storing software code. The processor executes the software code to receive a first rendered image having first color and auxiliary buffers, receive a second rendered image having second color and auxiliary buffers, provide a third auxiliary buffer for an intermediate image to be interpolated, and identify one or more context features from each of the color buffers and the auxiliary buffers. The software code further interpolates, based on the context features, the intermediate image to provide an interpolated image, determines, based on the one or more context features from each of the first, second, and third auxiliary buffers, a rendering mask for producing one or more rendered sub-portions of the intermediate image, partially renders, using the rendering mask, the intermediate image to provide a partially rendered image, and blends the interpolated image and the partially rendered image to provide a composite image.

Abstract: Techniques for aligning object representations for animation include analyzing a source object representation and a target object representation to identify a category of the source object and a category of the target object. Based on the category or categories of the objects, a feature extraction machine learning models is selected. The source object representation and the target object representation are provided as input to the selected feature extraction machine learning model to generate respective semantic descriptors and shape vectors for the source and target objects. Based on the semantic descriptors and the shape vectors for the source and target objects, an alignment machine learning model generates an aligned target object representation that is aligned with the source object representation and usable for animating the target object.

Abstract: A method performed by a computer is disclosed. The method comprises receiving color data for input pixels of an input image and an input set of features used to render the input image of a three-dimensional animation environment, wherein the input pixels are of a first resolution. The computer may then load into memory a generator of a generative adversarial network including a neural network used to scale the input image, the neural network trained using training data comprising color data of training input images and training output images and a training set of the features used to render the training input images. After the generator is loaded into memory, the computer may generate an output image having a second resolution that is different than the first resolution by passing the color data and the input set of features through the generator.

Abstract: Systems and methods generate a modified three-dimensional mesh representation of an object using a trained neural network. A computer system receives a set of input values for posing an initial mesh defining a surface of a three-dimensional object. The computer system provides the input values to a neural network trained on posed meshes generated using a rigging model to generate mesh offset values based upon the set of input values and the initial mesh. The neural network includes an input layer, an output layer, and a plurality of intermediate layers. The computer system generates, by the output layer of the neural network, a set of offset values corresponding to a set of three-dimensional target points based on the set of input values. The offset values are applied to the initial mesh to generate a posed mesh. The computer system outputs the posed mesh for generating an animation frame.

Abstract: An internal combustion engine includes an engine block, a crankshaft configured to rotate about a crankshaft axis, a flywheel coupled to the crankshaft and positioned above the engine block, an outer housing positioned above the engine block and the flywheel, and an electric starting system. The electric starting system includes an electric motor and an energy storage device positioned above the flywheel and below the outer housing. The energy storage device is electrically coupled to the electric motor to power the electric motor. When the electric starting system is configured to rotate the crankshaft to start the engine when the electric starting system is activated.

Abstract: An internal combustion engine includes an engine block, a crankshaft configured to rotate about a crankshaft axis, a flywheel coupled to the crankshaft and positioned above the engine block, an outer housing positioned above the engine block and the flywheel, and an electric starting system. The electric starting system includes an electric motor and an energy storage device positioned above the flywheel and below the outer housing. The energy storage device is electrically coupled to the electric motor to power the electric motor. When the electric starting system is configured to rotate the crankshaft to start the engine when the electric starting system is activated.

Abstract: An engine including an engine block having a cylinder defining a front of the engine, a blower housing coupled to the engine block and defining a hot half positioned adjacent the front of the engine and a cool half opposite the hot half, and an electric starter system positioned within the blower housing. The electric starting system includes a starter mount assembly coupled to the blower housing, an electric starter motor retained by the starter mount assembly and positioned in the cool half, and a battery mounted to the blower housing and positioned in the cool half. The battery is electrically coupled to the electric starter motor.

Abstract: A modular architecture is provided for denoising Monte Carlo renderings using neural networks. The temporal approach extracts and combines feature representations from neighboring frames rather than building a temporal context using recurrent connections. A multiscale architecture includes separate single-frame or temporal denoising modules for individual scales, and one or more scale compositor neural networks configured to adaptively blend individual scales. An error-predicting module is configured to produce adaptive sampling maps for a renderer to achieve more uniform residual noise distribution. An asymmetric loss function may be used for training the neural networks, which can provide control over the variance-bias trade-off during denoising.

Abstract: An internal combustion engine includes an engine block, a blower housing configured to direct cooling air to the engine block, an electric starting system, and a crankshaft configured to rotate about a crankshaft axis. The electric starting system includes an electric motor and an energy storage device located within the blower housing. The energy storage device is electrically coupled to the electric motor to power the electric motor, and is positioned above the crankshaft. When the starter motor is activated, the electric starting system rotates the crankshaft to rotate the engine for starting.

Abstract: A modular architecture is provided for denoising Monte Carlo renderings using neural networks. The temporal approach extracts and combines feature representations from neighboring frames rather than building a temporal context using recurrent connections. A multiscale architecture includes separate single-frame or temporal denoising modules for individual scales, and one or more scale compositor neural networks configured to adaptively blend individual scales. An error-predicting module is configured to produce adaptive sampling maps for a renderer to achieve more uniform residual noise distribution. An asymmetric loss function may be used for training the neural networks, which can provide control over the variance-bias trade-off during denoising.

Abstract: An engine including an engine block having a cylinder defining a front of the engine, a blower housing coupled to the engine block and defining a hot half positioned adjacent the front of the engine and a cool half opposite the hot half, and an electric starter system positioned within the blower housing. The electric starting system includes a starter mount assembly coupled to the blower housing, an electric starter motor retained by the starter mount assembly and positioned in the cool half, and a battery mounted to the blower housing and positioned in the cool half. The battery is electrically coupled to the electric starter motor.

Abstract: One embodiment of the present invention sets forth a technique for performing frame interpolation. The technique includes generating (i) a first set of feature maps based on a first set of rendering features associated with a first key frame, (ii) a second set of feature maps based on a second set of rendering features associated with a second key frame, and (iii) a third set of feature maps based on a third set of rendering features associated with a target frame. The technique also includes applying one or more neural networks to the first, second, and third set of feature maps to generate a set of mappings from a first set of pixels in the first key frame to a second set of pixels in the target frame. The technique further includes generating the target frame based on the set of mappings.

Abstract: Embodiments of the present invention are directed to methods and systems for treating irrigation water by introducing a propagating electromagnetic field into the irrigation water as it flows through an irrigation system. The treatments described herein may have a variety of beneficial effects when applied to hydrophobic soils, including a significant increase in the percentage of the water that is maintained in the root zone of a given crop as plant-available water and the essential mineral, e.g. calcium and/or magnesium, uptake of that crop. The treatments described herein may also have beneficial effects when applied to hydrophilic soils, and particularly high salinity, hydrophilic soils, including a reduction in the soil salinity, including the amount of chlorates, within a root zone of a crop.

Abstract: A method of self-administration of growth factors, polypeptides and other therapeutic agents, derived from pluripotent stem cells, via a non-invasive application, and formulated and offered as a kit for reduced cost, improved storage, increased ease, and increased convenience of practitioner, partner, care assistant, or end-user administration.

Abstract: An engine including an engine block having a cylinder defining a front of the engine, a blower housing coupled to the engine block and defining a hot half and a cool half opposite the front half, a starter mount assembly coupled to the blower housing and positioned within the cool half, an electric starter motor retained by the starter mount assembly, and a battery mounted to the blower housing and positioned in the cool half. The battery is electrically coupled to the electric starter motor.