287 results about "Render Target" patented technology

One embodiment of the invention sets forth a technique for efficiently combining two graphics processing units (“GPUs”) to enable an improved price-performance tradeoff and better scalability relative to prior art multi-GPU designs. Each GPU's memory interface is split into a first part coupling the GPU to its respective frame buffer and a second part coupling the GPU directly to the other GPU, creating an inter-GPU private bus. The private bus enables higher bandwidth communications between the GPUs compared to conventional communications through a PCI Express™ bus. Performance and scalability are further improved through render target interleaving; render-to-texture data duplication; data compression; using variable-length packets in GPU-to-GPU transmissions; using the non-data pins of the frame buffer interfaces to transmit data signals; duplicating vertex data, geometry data and push buffer commands across both GPUs; and performing all geometry processing on each GPU.

The invention provides, in some aspects, methods and apparatus for registering 3D image volumes by utilizing a graphics processing unit (GPU) to facilitate maximizing the “mutual information” of the two image volumes being registered. Particularly, the GPU is used to compute a histogram representing a probability that a pixel value in one of the images being registered coincides with a pixel value in a transform of the other image. In one aspect, this histogram is generated by a two-step approach including (i) “drawing” a polygon covering a two-component render target having as many pixels as there are samples, where the value of each pixel in the target includes the intensities of the respective pixels of the first and second images, (ii) interpreting that render target as a buffer of vertex positions and, for each sample, rendering into a new render target, a single vertex using coordinates from that buffer.

The invention provides a method and a device for graphic rendering on a mobile device. The method includes acquiring a JavaScript code of a graphic application program; executing the JavaScript code in an analysis engine; calling a rendering function acquired by the analysis to perform graphic rendering on a rendering target. The JavaScript code includes an API (application program interface) corresponding to an OPENGL (open graphics library)-based rendering function, and the pattern of the API follows the HTML5 (hypertext markup language 5) Canvas standard. The execution process of the JavaScript code includes using the analysis engine to analyze the API as the corresponding OPENGL-based rendering function when the API in the JavaScript code is executed. By the method and the device, speed of graphic rendering on the mobile device can be increased.

A content-aware image retargeting technique uses an “importance filtering” technique to preserve important information in the resizing of an image. The image saliency is first filtered, guided by the image itself to achieve a structure-consistent importance map. The pixel importance is then used as the key constraint in computing the gradient map of pixel shifts from the original resolution to the target resolution. Finally the shift gradient is integrated across the image by a weighted filtering process to construct a smooth pixel shift-map and render the target image. The weight is again controlled by the pixel importance. The two filtering processes enforce the maintaining of structural consistency while preserving the important contents in the target image. The simple nature of the present filter operations allow for real-time applications and easy extension to video retargeting, as the structural constraints from the original image naturally convey the temporal coherence between frames.

A framework for performing graphics animation and compositing operations has a layer tree for interfacing with the application and a render tree for interfacing with a render engine. Layers in the layer tree can be content, windows, views, video, images, text, media, or any other type of object for a user interface of an application. The application commits change to the state of the layers of the layer tree. The application does not need to include explicit code for animating the changes to the layers. Instead, an animation is determined for animating the change in state. In determining the animation, the framework can define a set of predetermined animations based on motion, visibility, and transition. The determined animation is explicitly applied to the affected layers in the render tree. A render engine renders from the render tree into a frame buffer for display on the computer system. Those portions of the render tree that have changed relative to prior versions can be tracked to improve resource management.

A variable data pantograph is formed by receiving a variable data string and retrieving at least one character representation from a vocabulary of character representations stored in memory. The retrieved at least one character representation corresponds to the variable data string. Each of the character representations in the vocabulary is associated with a foreground region including a character shape and a background region suitably sized and arranged for encompassing the foreground region. The background region incorporates a first pattern of elements and is controlled to render a target color using a first set of color separation control data and the foreground region incorporates a second pattern of elements and is controlled to render the target color using a second set of color separation control data. The retrieved at least one character representation is assembled to form a variable data pantograph, whereby when the variable data pantograph is rendered in an original document, the foreground and background regions are similar in tone, the foreground and background regions being substantially less similar in tone in a copy of the original document to render the character visible.

The embodiment of the invention discloses an image processing method, an image processing device and computer equipment. The image processing method disclosed by the embodiment of the invention comprises the following steps that: a graphics processor receives information, sent by a central processing unit, of a scene in a preset range around a target object to be rendered; the graphics processor renders the received scene to obtain a scene depth parameter, and the scene is obtained through being shot by a camera positioned in a position of a ray light source; the graphics processor renders a target object to be rendered to obtain a rendering depth parameter, and the target object to be rendered is obtained through being shot by a camera not positioned at in a position of the ray light source; the graphics processor calculates the environment light shielding picture of the target object to be rendered in each ray light source direction according to the scene depth parameter and the rendering depth parameter; and the graphics processor carries out stacking on the environment light shielding pictures in each ray light source direction to obtain an output image. The image processing method, the image processing device and the computer equipment provided by the embodiment of the invention have the advantage that the image processing efficiency can be improved.

A rendering processing apparatus is provided which performs occlusion culling for excluding from rendering targets a hidden object behind another object as seen from a point of view, when given a plurality of objects. An object input unit stores a plurality of objects in an object storing unit. An internal volume generating unit generates an internal volume which is included in a target object. A reduced Z-buffer updating unit updates a reduced Z-buffer based on the internal volume. An external volume generating unit generates an external volume which includes the target object subject to culling test. A culling determination unit consults the reduced Z-buffer and performs a Z culling test on the target object based on the external volume.

The invention discloses an expression synthesis method and device based on phoneme driving and a computer storage medium, and the method mainly comprises the steps: recognizing a target voice text according to a preset database, so as to obtain a phoneme sequence, and converting the phoneme sequence into a replacement expression parameter sequence; extracting to-be-replaced original sub-video datafrom the original video data based on the voice duration of the target voice text; constructing a three-dimensional face model based on faces in the original sub-video data, extracting to-be-replacedexpression parameters of the three-dimensional face model frame by frame to generate a to-be-replaced expression parameter sequence, and replacing the to-be-replaced expression parameter sequence with the replaced expression parameter sequence; utilizing the replacement expression parameter sequence to drive a three-dimensional face model to generate a target two-dimensional image sequence, and rendering the target two-dimensional image sequence frame by frame; and splicing the rendered target two-dimensional image sequence to generate target sub-video data for replacing the original sub-video data. According to the invention, the expression synthesis video with a more real effect can be efficiently and accurately obtained.

In a multiple render target mode, a pixel shader computes color values for pixels and stores the computed color values in a register file. The register file acts as a buffer for the computed color values. Conventionally writing pixels in the order they are received (pixel-major order) can result in large strides across memory in the frame buffer. At least a minimum amount of work should be done within a DRAM page, for example, to cover the overhead required in opening the DRAM page. Therefore, color values are written from the register file to two or more targets in a frame buffer in a target-major order within a segment. Writing in a target-major order (sequential with respect to targets but non-sequential with respect to quads received and processed) yields coherent writes to frame buffer memory and improves memory efficiency.

A method for managing bind-render-target commands in a tile-based architecture. The method includes receiving a requested set of bound render targets and a draw command. The method also includes, upon receiving the draw command, determining whether a current set of bound render targets includes each of the render targets identified in the requested set. The method further includes, if the current set does not include each render target identified in the requested set, then issuing a flush-tiling-unit-command to a parallel processing subsystem, modifying the current set to include each render target identified in the requested set, and issuing bind-render-target commands identifying the requested set to the tile-based architecture for processing. The method further includes, if the current set of render targets includes each render target identified in the requested set, then not issuing the flush-tiling-unit-command.

The invention discloses a picture rendering method and a device, a storage medium and an electronic device. The method comprises the following steps of: determining a target picture to be rendered ina two-dimensional virtual scene to be rendered by a client, wherein, the target picture comprises a background picture and a character object moving on the background picture, and the background picture comprises a target object located at a fixed position; Determining a first depth value corresponding to pixel points on a target object in a background picture by using a depth offset indicated ina depth map corresponding to the target object, wherein depth maps record depth offsets of pixel points on the target object; Acquiring a second depth value corresponding to a pixel point on the character object moved to the current display position; The target picture is rendered according to the first depth value and the second depth value. The invention solves the technical problem of low accuracy of rendering two-dimensional picture information in the related art.