Abstract: The present disclosure provides a screen detection method, an apparatus and a device, a computer program and a readable medium, and belongs to the technical field of screens. The method includes: receiving a cylindrical lens detection instruction for a target screen, wherein the cylindrical lens detection instruction at least includes target viewpoints; acquiring browsing images shot from the target screen under the target viewpoints in response to the detection instruction, wherein the target screen is a screen of which the light emission side is provided with cylindrical lenses; using the browsing images as viewpoint images under the condition that the browsing images include target contents; and outputting detection parameters of the cylindrical lenses on the target screen based on image parameters of the viewpoint images.

Abstract: A display panel includes a plurality of sets of pixel strips extending in a first direction and arranged in a second direction, each set of pixel strips includes a plurality of sub-pixel strips in different colors, spacing between every two adjacent sub-pixels in each sub-pixel strip in the first direction is smaller than or equal to 2 ?m, each set of pixel strips is divided into a plurality of pixel islands arranged in an array in the first direction, each pixel island includes at least four sub-pixels extending in the first direction in each corresponding sub-pixel strip, a width of a view region formed by light emitted by each sub-pixel in each pixel island being propagated to a human eye through a corresponding lens is smaller than or equal to a pupil diameter.

Abstract: The present disclosure provides a three-dimensional display device, a driving method and manufacturing method therefor.

Abstract: A display apparatus, including: the display panel includes multiple pixel islands arranged at intervals in a row direction and a column direction; odd rows of pixel islands and even rows of pixel islands are staggered in the row direction, and odd adjacent boundaries, extending in the column direction, of any two adjacent odd and even columns of pixel islands are colinearly arranged. Each pixel island includes multiple sub-pixels arranged at intervals in the row direction and the column direction, rows of sub-pixels in each pixel island are staggeredly arranged in sequence in the row direction, and adjacent boundaries, extending in the column direction, of any two adjacent columns the sub-pixels are collinearly arranged; and the light-splitting assembly is at a display surface side of the display panel and includes multiple lenses that extend in the column direction and are arranged at intervals in the row direction.

Abstract: Provided are a display apparatus and a method for manufacturing the same. The display apparatus comprises: a display panel, which comprises a plurality of pixel groups, wherein each pixel group comprises a plurality of pixels; a light-transmitting spacer layer, which is located on a light-emitting side of the display panel; and an imaging structure, which is located on the side of the light-transmitting spacer layer facing away from the display panel, and comprises a light-shielding layer, wherein the light-shielding layer comprises a plurality of light-transmitting holes matching the pixel groups, light rays emitted by the pixels pass through the light-transmitting holes, and light rays emitted by at least two pixels pass through the light-transmitting holes so as to simultaneously enter a monocular pupil of a user.

Abstract: A light field display method includes: generating a pixel light field information database (S1); processing, according to different depth positions of an original three-dimensional image, slice images corresponding to the different depth positions and pixel light field information at the different depth positions, to obtain recorded images of the slice images of the original three-dimensional image at the different depth positions (S2); and superimposing the recorded images of the slice images of the original three-dimensional image at the different depth positions, to obtain a microcell array image of the original three-dimensional image (S3). A light field display system has a database generator (101), a recorded image generator (102), and a superimposer (103) which implement the described functions. A non-transitory computer readable storage medium stores thereon a computer program for implementing the method. A display panel includes the non-transitory computer readable storage medium.

Abstract: A method of performing multidimensional magnetic resonance imaging on a subject comprises collecting imaging data for a region of interest of the subject, the imaging data related to one or more spatially-varying parameters of the subject within the region of interest; collecting auxiliary data for the region of interest in the subject, the auxiliary data related to one or more time-varying parameters of the subject within the region of interest; linking the imaging data and the auxiliary data; and constructing an image tensor with one or more temporal dimensions based on at least a portion of the linked imaging data and at least a portion of the linked auxiliary data.

Abstract: The disclosure provides a display apparatus and a driving method. The display apparatus includes: a display panel, where the display panel includes a plurality of pixel islands arranged in arrays in a row direction and a column direction, and each pixel island includes n sub-pixels arranged at intervals in the row direction, where n is greater than 1; and a light-splitting component at a display side of the display panel, where the light-splitting component includes a plurality of light-splitting repeating units extending in the column direction and continuously arranged in the row direction, the light-splitting repeating unit includes M light-splitting structures extending in the column direction and continuously arranged in the row direction, each light-splitting repeating unit correspondingly covers K columns of pixel islands, both M and K are integers greater than 1, and M and K are prime to each other.

Abstract: The present disclosure relates to a 3D display device, includes: a display panel; a lens layer arranged on a light exit side of the display panel, and including a plurality of convergent lenses arranged in an array; a human eye tracker provided on a side of the lens layer away from the display panel, the human eye tracker being used to determine spatial positions of one or more viewers' eyes relative to the display panel when facing the display panel; and a controller electrically connected to the display panel and the human eye tracker, the controller being used to receive the spatial positions and control subpixels of the display panel corresponding to the spatial positions to display image slices corresponding to the spatial positions.

Abstract: A texture recognition assembly (100) includes: a substrate (1); an optical sensing structure (2) on the substrate; and a light path structure (3) on a side of the optical sensing structure distal to the substrate and including an inclined light transmitting channel (Q) such that light incident on the light path structure can only pass through the light transmitting channel. The light path structure includes at least two light shielding layers (31, 31a, 31b, 31c) and a light transmitting layer (32, 32a, 32b) located between any adjacent two of the at least two light shielding layers, the light shielding layer (31a) closest to the optical sensing structure includes a first light transmitting hole (311a) the light shielding layer (31b) farthest away from the optical sensing structure includes a second light transmitting hole (322b), the first light transmitting hole and the second light transmitting hole define the light transmitting channel.

Abstract: A device for deep learning acceleration with mixed precision may include a precision mode port configured to receive an indication of an output precision mode, a data input port configured to receive an input value, and a truncation component configured to truncate the input value into a keep segment value and a truncate segment value. The device may be configured to add the keep segment value and a carry bit to generate a rounded keep segment value, and to generate a rounded output based on the rounded keep segment value and the output precision mode. The rounded output generation component may be configured to generate the rounded output to include a sign bit of the keep segment value and either a first quantity or a second quantity of lower bits of the keep segment value based on the output precision mode being either a first value or a second value.

Abstract: A device for deep learning acceleration with mixed precision may include a first precision mode port to receive an indication of an input precision mode and a second precision mode port to receive an indication of an output precision mode. The device may include a first data port to receive map data and a second data port to receive kernel data. The device may include multiply-accumulate (MAC) components that are each configured to generate a MAC output based on the input precision mode, the map data, and the kernel data. The device may include an adder component to generate an adder component output based on the input precision mode and one or more MAC outputs. The device may include a rounding component to round the adder component output, based on the output precision mode, to generate a rounded output, and an output port to output the rounded output.

Abstract: A device for deep learning acceleration with mixed precision may include a token generator configured to generate a token value and may include multiple multiplexers. Each multiplexer may include a load port configured to receive map data, a max pool port configured to receive max pool data, and matrix-matrix (MM) data input ports each configured to receive MM data based on MM output generated by an MM component. Each multiplexer may include an output port configured to provide output data to a single MM component. Each multiplexer may provide corresponding output data to a different MM component. Each multiplexer may be configured to select, based on the token value, an input from one of the load port, the max pool port, or a single MM data input port, of the MM data input ports, as the output data to be provided to the output port.

Abstract: A device for deep learning acceleration with mixed precision may include multiple matrix-matrix (MM) components that each include multiple map memory components configured to store map data, multiple kernel memory components configured to store kernel data, and multiple matrix-vector (MV) components. The MV components may each include multiple vector-vector (VV) components that are each configured to generate a VV output based on an input precision mode, an output precision mode, and an accumulation of products that is based on the map data and the kernel data. Each VV component included in a particular MV component may be coupled with each map memory component and may be coupled with a single kernel memory component. The device may include a data distribution component coupled with the multiple MM components and configured to load the map data into the multiple map memory components.

Abstract: A device for deep learning acceleration with mixed precision may include a first data port configured to receive a map data segment and a second data port configured to receive a kernel data segment. The device may include a precision mode port configured to receive an indication of an input precision mode that indicates a word length for the map data segment and for the kernel data segment. The device may include a multiplier component configured to generate a multiplier component output based on the input precision mode and based on multiplying the map data segment and the kernel data segment. The device may include an adder component configured to generate an adder component output based on the input precision mode and based on the multiplier component output. The device may include an output port configured to output the adder component output.

Abstract: A device for deep learning acceleration with mixed precision may include vector-vector (VV) components that are each configured to generate a VV output based on an input precision mode, an output precision mode, and at least one accumulation of products. Each accumulation of products may be calculated by adding products based on the input precision mode. Each product may be calculated by multiplying a map word and a kernel word based on the input precision mode. The input precision mode may indicate an input word length for the map word and for the kernel word, and the output precision mode may indicate an output word length for the VV output. The device may include one or more components configured to concatenate VV outputs, corresponding to the VV components, to generate a concatenated VV output. The device may include an output port configured to output the concatenated VV output.

Abstract: A device for deep learning acceleration with mixed precision may include matrix-vector (MV) components that each include vector-vector (VV) components that are each configured to generate a respective VV output based on an input precision mode, an output precision mode, and an accumulation of products. The accumulation of products may be calculated by adding products based on the input precision mode. Each product may be calculated by multiplying, based on the input precision mode, a map data segment and a kernel data segment. Each MV component may include one or more components configured to concatenate VV outputs to generate a concatenated VV output. The device may include activation function components that are each configured to receive a corresponding concatenated VV output, generate an activation function output based on the corresponding concatenated VV output and the output precision mode, and output the activation function output.

Abstract: The present disclosure relates to a display assembly, a display device and a driving method. The display assembly includes: a display panel provided with a plurality of pixel islands distributed in an array, any one of the pixel islands including sub-pixels continuously arranged along a set direction; and a lens layer arranged on a light exit surface of the display panel and including lenses arranged along the set direction. A lenticular lens pitch is not greater than a size of an opening of each pixel island in the set direction, and along the set direction, a sub-pixel pitch in each of the pixel islands is smaller than a half of the lenticular lens pitch. The lenticular lens pitch is equal to a sum of a size of each lenticular lens in the set direction and a distance between two adjacent ones of the plurality of lenticular lenses.

Abstract: Methods, systems, and apparatuses related to computational storage are described. For example, storage accessible to an accelerator may be shared between and, accessible to either of, a host and the accelerator. A computational storage system may include storage providing a portion of a shared file system accessible by a host and by accelerator logic of the computational storage system. Host interface logic may be configured to receive a storage command from the host to store data on the storage at a time the data is created. The host interface logic may be further configured to receive a storage command from the host for the accelerator logic to perform a computational task using the stored data on the storage. The accelerator logic can perform the computational task using the stored data on the storage.

Abstract: An optical waveguide includes an optical waveguide body having a beam in-coupling region and a beam coupling-out region, wherein: the beam in-coupling region is provided with a coupling grating configured to couple a beam into the optical waveguide body, and have the beam propagate in a total reflection manner in the optical waveguide body; the beam coupling-out region is provided with an out-coupling grating configured to couple the light beam propagating to the beam coupling-out region out of the optical waveguide body, such that the beam does not undergo secondary diffraction at the coupling grating and have continuous exit pupil expansion; and the out-coupling grating includes a transmissive out-coupling grating and a reflective out-coupling grating disposed on two sides of the optical waveguide body parallel to a beam propagation direction.