Abstract: A computer system may receive a layout of a data center, the layout of the data center identifying physical locations of a plurality of server racks, electrical distribution feeds, and uninterruptible power supplies. The computer system may receive a fault domain configuration for the datacenter, the fault domain configuration identifying virtual locations of a plurality of logical fault domains for distributing one or more instances so that the instances are stored on independent physical hardware devices within a single availability fault domain. The computer system may determine the configuration for the data center by assigning the plurality of fault domains to a plurality of electrical zones, wherein each electrical zone provides a redundant electrical power supply across the plurality of logical fault domains in an event of a failure of one or more electrical distribution feeds. The computer system may display the configuration for the data center on a display.

Abstract: A system includes a machine learning (ML) model-based video encoder configured to receive an uncompressed video sequence including multiple video frames, determine, from among the multiple video frames, a first video frame subset and a second video frame subset, encode the first video frame subset to produce a first compressed video frame subset, and identify a first decompression data for the first compressed video frame subset. The ML model-based video encoder is further configured to encode the second video frame subset to produce a second compressed video frame subset, and identify a second decompression data for the second compressed video frame subset. The first decompression data is specific to decoding the first compressed video frame subset but not the second compressed video frame subset, and the second decompression data is specific to decoding the second compressed video frame subset but not the first compressed video frame subset.

Abstract: An apparatus applies traction to a digit of a patient's foot at a desired adduction angle and a desired dorsiflexion angle, for use in treating a bunion. The apparatus includes: a shoe portion (e.g., a sole, and strap(s)); a digit attachment apparatus (e.g., a Chinese finger trap) having a cable extending therefrom; and an apparatus (e.g., a ratchet, an actuator, and the like) configured to apply tension to the cable with respect to the sole. A support bracket is configured to pivot with respect to the shoe portion to adjust the adduction angle of the cable with respect to an axial direction of the sole, and is further configured to extend upwardly to at an elevated position with respect to the sole. An adjustment member is mounted to slide relative to the support bracket, to adjust the dorsiflexion angle provided by the cable independent of the adduction angle.

Abstract: One embodiment of the present invention sets forth a technique for performing face swapping. The technique includes converting a first input image that depicts a first facial identity from a first viewpoint at a first time into a first latent representation and converting a second input image that depicts the first facial identity from a second viewpoint at the first time into a second latent representation. The technique also includes generating, via a first machine learning model, a first output image that depicts a second facial identity from the first viewpoint based on the first latent representation. The technique further includes generating, via the first machine learning model, a second output image that depicts the second facial identity from the second viewpoint based on the second latent representation.

Abstract: One embodiment of the present invention sets forth a technique for inserting content into a media program. The technique includes determining a plurality of markers corresponding to a plurality of locations within a media program. The technique also includes for each marker included in the plurality of markers, automatically analyzing a first set of intervals within the media program that lead up to the marker and a second set of intervals within the media program that immediately follow the marker and determine a set of audio characteristics associated with the first set of intervals and the second set of intervals. The technique further includes generating a plurality of scores for the plurality of markers based on the set of audio characteristics for each marker and inserting additional content at one or more markers included in the plurality of markers based on the plurality of scores.

Abstract: Embodiments of the present disclosure provide techniques for colorizing visual content using artificial intelligence models. An example method generally includes receiving an image and an input prompt specifying a colorization to apply to the image. Based on an encoded version of the image and a textual description of the image input into a machine learning model, one or more color maps associated with the specified colorization to apply to the image are generated. A colorized version of the image is generated by a generative artificial intelligence model based on combining a grayscale version of the image and the one or more color maps, and the colorized version of the image is output.

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: Embodiments of the present invention are directed to security systems for securing an item of merchandise from theft or unauthorized removal. For example, the security system may include a sensor configured to be coupled to the item of merchandise, wherein the sensor includes an electrical connector. The security system also includes a base configured to removably support the sensor thereon, wherein the base includes an electronics module having a connector. The connector of the sensor and the connector of the electronics module are configured to electrically connect with one another when the sensor is supported on the base, and the sensor is configured to detect unauthorized removal of the item of merchandise from the sensor.

Abstract: A metrology system includes an illumination configuration having an illumination source, an objective lens configuration, and an image sensor configuration including an image sensor. The objective lens configuration includes an objective lens and has a lens optical axis. The illumination configuration, the objective lens configuration and the image sensor configuration form an optical path along which illumination from the illumination configuration travels. The illumination configuration provides illumination in an illumination direction toward at least a portion of an edge of a circular workpiece that is along the optical path. At least part of the illumination configuration is tilted relative to the objective lens configuration such that the illumination direction is at a first tilt angle in relation to the lens optical axis.

Abstract: A system includes a machine learning (ML) model-based video downsampler configured to receive an input video sequence having a first display resolution, and to map the input video sequence to a lower resolution video sequence having a second display resolution lower than the first display resolution. The system also includes a neural network-based (NN-based) proxy video codec configured to transform the lower resolution video sequence into a decoded proxy bitstream. In addition, the system includes an upsampler configured to produce an output video sequence using the decoded proxy bitstream.

Abstract: One aspect of this invention relates to a harp with a novel chromatic string arrangement. Another aspect of this invention relates to a frame structure to support said string arrangement which is shield shaped.

Abstract: A storage system and a load handling device for lifting and moving containers stacked in the storage system are described. The storage system includes a plurality of rails or tracks arranged in a grid pattern above the stacks of containers. The grid pattern can include a plurality of grid spaces and each stack is located within a footprint of only a single grid space. The load handling device is configured to move laterally on the rails or tracks above the stacks. The load-handling device includes a container-receiving space located above the rails or tracks in use and a lifting device arranged to lift a container from a stack into the container-receiving space. The load handling device has a footprint that, in use, occupies only a single grid space in the storage system.

Abstract: A measuring probe for a coordinate measuring machine is provided. The measuring probe includes a stylus position detection portion, signal processing and control circuitry and a temperature dependent compensation portion. The stylus position detection portion includes a field generating coil configuration and a sensing coil configuration. The temperature dependent compensation portion includes a temperature dependent component that is coupled to a field generating coil of the field generating coil configuration such that a change in a characteristic of the temperature dependent component due to an increase in temperature of the temperature dependent component causes relatively more current to flow through the field generating coil when driven by the coil drive signal than if the characteristic of the temperature dependent component had not changed.

Abstract: One embodiment of the present invention sets forth a technique for generating a quad-dominant mesh of an object. The technique includes generating, via at least one of a first set of machine learning models, a three-dimensional (3D) triangle mesh of an object based on one or more two-dimensional input images of the object, iteratively learning, via a second set of machine learning models, an orientation field and a position field associated with a set of vertices included in the 3D triangle mesh, extracting a quad-dominant mesh associated with the object from the input triangle mesh based on the orientation field and the position field, wherein the quad-dominant mesh comprises one or more quadrilaterals, rendering an image based on the quad-dominant mesh; and optimizing the quad-dominant mesh by propagating a loss generated based on the image to the set of machine learning models.

Abstract: A system includes a tunable neural network-based video encoder configured to receive a video sequence including multiple video frames, generate a frame-specific embedding of a first video frame of the multiple video frames, and identify one or more group-of-pictures (GOP) features of a subset of the multiple video frames, the subset of the including the first video frame. The tunable neural network-based video encoder is further configured to combine the frame-specific embedding of the first video frame and the one or more GOP features of the first plurality of the plurality of video frames to provide a latent feature corresponding to a compressed version of the first video frame.

Abstract: In some embodiments, a method receives a quantized latent representation of an image in a latent space. The image is encoded into a representation in the latent space and quantized to generate the quantized latent representation. A time step parameter is received that is generated based on the representation. The method performs an inverse quantization process to generate a reconstructed representation. A diffusion model performs a denoising process for a number of iterations based on the time step parameter to remove noise from the reconstructed representation to generate a denoised reconstructed representation. The denoised reconstructed representation is decoded into a reconstructed image.

Abstract: In some embodiments, a method determines an anchor image and a first mapping of a grid to the anchor image. The anchor image includes a first value of a characteristic and the grid includes a second value. Input images and second mappings between respective input images and the anchor image is determined. The method determines a query value for the grid based on features extracted from a location in the anchor image that is determined from the first mapping of the grid. Keys and values for each of the input images is determined based on respective input images and respective second mappings. The method weights values of the input images based on comparing the query value and the respective keys to generate weighted values. The weighted values are used to generate a feature value in a feature map. The method generates an output image from the feature map.

Abstract: Various enhancements to grid-interactive inverters in accordance with embodiments of the invention are disclosed. One embodiment includes input terminals configured to receive a direct current, output terminals configured to provide an alternating output current to the utility grid, a controller, an output current sensor, and a DC-AC inverter stage comprising a plurality of switches controlled by control signals generated by the controller. In addition, the controller is configured to: generate control signals that cause the switches in the DC-AC inverter stage to switch a direct current in a bidirectional manner; measure the alternating output current; perform frequency decomposition of the output current; and generate control signals that cause the switches in the DC-AC inverter stage to switch current in a way that the magnitude of a plurality of unwanted current components is subtracted from the resulting output current.

Abstract: The present invention sets forth a technique for performing resampling of a deep image. The technique includes receiving a deep image, where the deep image includes one or more channel sample values, each channel sample value including one or more associated depth values and partitioning the deep image into one or more three-dimensional (3D) regions, wherein each 3D region is defined by one or more planar surfaces each including an associated depth value. The technique also includes generating an upsampled image having a greater resolution than the deep image and interpolating, based on a specified interpolation technique, one or more new channel sample values associated with pixels included in the upsampled image. The technique further includes generating an output deep image based on the upsampled image and the one or more new channel sample values.

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.