Abstract: Provided are a method and system for novel-view image synthesis and rendering, a device and a medium. The method includes: acquiring initial information of a target model; performing neural texturing on the initial information to obtain neural texture (NT) information; and inputting the NT information to a synthesis rendering model to obtain a rendered image, where the synthesis rendering model includes an NT input module, an NT learning network module, and a differentiable renderer that are connected to each other; the NT input module receives the NT information, and transmits the NT information to the NT learning network module; the NT learning network module performs convolution and activation as well as concatenation on the NT information to obtain NT processed information; and the differentiable renderer adjusts and renders the NT processed information in a neural rendering manner to obtain the rendered image.

Abstract: An image rendering system for rendering two-dimensional images in real-time. The image rendering system can receive an implicit representation model of a three-dimensional image. The image rendering system can construct, based on voxel coordinates, a three-dimensional image based on the implicit representation model. The image rendering system can rotate the three-dimensional image to an orientation in a computing space based on a user input. The image rendering system can generate a two-dimensional image based on the rotated three-dimensional image.

Abstract: A computing system for encoding a machine learning model comprises a plurality of layers and a plurality of computation units. A first set of computation units are configured to process data at a first bit width. A second set of computation units are configured to process at a second bit width. The first bit width is higher than the second bit width. A memory is coupled to the computation units. A controller is coupled to the computation units and the memory. The controller is configured to provide instructions for encoding the machine learning model. The first set of computation units are configured to compute a first set of layers and the second set of computation units are configured to compute a second set of layers.

Abstract: A computing core for rendering an image computing core comprises a position encoding logic and a plurality of pipeline logics connected in series in a pipeline. The position encoding logic is configured to transform coordinates and directions of sampling points corresponding to a portion of the image into high dimensional representations. The plurality of pipeline logics are configured to output, based on the high dimensional representation of the coordinates and the high dimensional representation of the directions, intensity and color values of pixels corresponding to the portion of the image in one pipeline cycle. The plurality of pipeline logics are configured to run in parallel.

Abstract: The present invention discloses a stereo garage that comprises: a main body provided with a lifting shaft, wherein the lifting shaft is provided with an opening; a lifting platform located in the lifting shaft, wherein the lifting platform can ascend or descend in the lifting shaft along a height direction of the main body, such that the lifting platform can switch between an initial position and an end position, wherein the lifting platform can close the opening when the lifting platform is located in the initial position; an anti-falling device connected to the main body, wherein the anti-falling device comprises a blocking rod which can be switched between a locking position and an unlocking position; wherein, the blocking rod can block a movement of a vehicle when the blocking rod is located in the locking position, and the lifting platform can cause the blocking rod to be switched from the locking position to the unlocking position when the lifting platform comes into the initial position.

Abstract: An image rendering system comprising a preprocessing unit coupled to a feature extract unit and a color rendering unit over a data bus. The preprocessing unit generates vector representations of spatial coordinates of sample points along camera rays corresponding to pixels of an image to be rendered. The feature extract unit generates a feature map of the image based on the vector representations, color and intensity values of the sample point through a first machine learning model. The color rendering unit renders the image based on the feature map through a second machine learning model. The first machine learning model is different from the second machine learning model.

Abstract: Aspects of direct current (DC)-DC converters with an integrated matrix transformer and multiphase current doubler rectifiers are described. In some examples, a DC-DC converter can include a matrix transformer that has multiple magnetically integrated transformer components that are magnetically integrated using transformer components that share a top plate and a bottom plate. A multiphase current doubler rectifier can include multiple synchronous rectifiers corresponding to the plurality of transformer components of the matrix transformer.

Abstract: A computer-implemented method includes encoding a radiance field of an object onto a machine learning model; conducting, based on a set of training images of the object, a training process on the machine learning model to obtain a trained machine learning model, wherein the training process includes a first training process using a plurality of first test sample points followed by a second training process using a plurality of second test sample points located within a threshold distance from a surface region of the object; obtaining target view parameters indicating a view direction of the object; obtaining a plurality of rays associated with a target image of the object; obtaining render sample points on the plurality of rays associated with the target image; and rendering, by inputting the render sample points to the trained machine learning model, colors associated with the pixels of the target image.

Abstract: Power converters with current doubler rectifier output stages, current doubler rectifier output stages, and integrated transformers for current doubler rectifier output stages and related output stages are described. In one example, a power converter includes a switched bridged input stage and a current doubler rectifier output stage comprising an integrated transformer. The integrated transformer of the current doubler rectifier output stage includes magnetic cores. A primary winding and a secondary winding of the integrated transformer extend around each of the plurality of magnetic cores, and the integrated transformer further includes a coupling winding that extends around each of the plurality of magnetic cores to provide magnetic integration among the plurality of magnetic cores through an electrical coupling.

Abstract: Aspects of direct current (DC)-DC converters with an integrated matrix transformer and multiphase current doubler rectifiers are described. In some examples, a DC-DC converter can include a matrix transformer that has multiple magnetically integrated transformer components that are magnetically integrated using transformer components that share a top plate and a bottom plate. A multiphase current doubler rectifier can include multiple synchronous rectifiers corresponding to the plurality of transformer components of the matrix transformer.

Abstract: Methods and structures for reducing and/or eliminating moisture penetration in an optical package. The optical package may include (1) a layer of inorganic material placed over the points of the optical package susceptible moisture penetration of the optical package; (2) a portion of hygroscopic material placed over the points of the optical package susceptible to moisture penetration; (3) a layer of hygroscopic material placed on the interior surface of the optical package; and/or (4) a layer of hydrophobic material coated on the optical surfaces of the optical package.

Abstract: An optical architecture and network is described that includes first and second transceivers coupled by an optical fiber. The first and second transceivers concurrently transmit and receive a plurality of optical signals that propagate in a first direction and at least one optical signal propagating in a second, opposite direction through the optical fiber. The network includes the first transceiver that uses a first means for combining the plurality of optical signals and a second means for transmitting the combined plurality of optical signals into the fiber in the first direction and for intercepting and redirecting the optical signal propagating from the fiber in the second, opposite direction. The network further includes the second transceiver that uses a third means for passing the optical signal propagating into the fiber in the second opposite direction and for redirecting the optical signals propagating from the fiber in the first direction.