42 results about "Texture atlas" patented technology

Systems and methods for displaying volume data on an arbitrary three-dimensional polygonal surface are disclosed. For each polygon in the polygonal surface, a two-dimensional texture tile is created and these texture tiles are combined to form texture atlases. Each texture atlas is allocated a specific amount of memory in a texture cache. Each polygon in the polygonal surface may be scan-converted and the resulting texels may be placed in the texture cache. Voxels that do not intersect any polygon in the polygonal surface may not be scan-converted. This method may result in reduced use of texture cache.

A method, apparatus, system, article of manufacture, and computer readable storage medium provide the ability to render point cloud data. After obtaining point cloud data, polygons are fit to the point cloud data. A texture atlas is created for each of the polygons. A lookup table is generated from the texture atlases and maps each pixel to a corresponding texture location. When a scene is loaded for rendering / processing, the polygons and texture atlas are loaded and projected into an off-screen buffer that defines a depth map of the scene with approximations of a depth per pixel in screen space. The off-screen buffer is used as a lookup table to determine texture data to be rendered for the scene.

An exemplary method for simplifying a texture of a three-dimensional model includes simplifying a first three-dimensional model to determine a second three-dimensional model. The first three-dimensional model has a higher resolution than the second three-dimensional model. The method also includes allocating a texture atlas for the second three-dimensional model. The method further includes filling in the texture atlas for the second three-dimensional model. Filling in the texture atlas may include determining a location on the second three-dimensional model corresponding to a pixel in the texture atlas for the second three-dimensional model, determining a location on the first three-dimensional model corresponding to the determined location on the second three-dimensional model, determining a color value texture mapped to the first three-dimensional model at the determined location on the first three-dimensional model, and setting the determined color value to the pixel in the texture atlas for the second three-dimensional model.

The invention discloses a texture rendering method and system for real-time three-dimensional human body reconstruction, a chip, equipment and a medium. The method comprises the steps of obtaining a current human body model and a depth image of a shooting object; selecting a current human body model as a standard model, reprojecting the vertex of the standard model to the depth image, extracting color information and image coordinates corresponding to the vertex, wherien the color information is a color initial value, and the image coordinates are converted into texture coordinates; calculating a weighted sum of the subsequent color information of the vertex of the human body model and the color initial value to serve as a new color of the vertex of the standard model; calculating sub-texture maps and sub-masks of the current human body model, and combining the sub-texture maps and the sub-masks into a complete texture map and mask; and performing rendering according to the texture mapand the texture coordinates. According to the method, generation and optimization of required textures can be rapidly completed based on the GPU, a high-quality texture atlas is obtained, and color cracks caused by illumination changes are eliminated. A human body model generated in a multi-camera system can be rendered, and a good visual reality sense is achieved.

Systems and methods are provided for optimizing the geometric stretch of a parametrization scheme. Given an arbitrary mesh, the systems and methods construct a progressive mesh (PM) such that all meshes in the PM sequence share a common texture parametrization. The systems and methods minimize geometric stretch, i.e., small texture distances mapped onto large surface distances, to balance sampling rates over all locations and directions on the surface. The systems and methods also minimize texture deviation, i.e., “slippage” error based on parametric correspondence, to obtain accurate textured mesh approximations. The technique(s) begin by partitioning the mesh into charts using planarity and compactness heuristics. Then, the technique(s) proceed by creating a stretch-minimizing parametrization within each chart, and by resizing the charts based on the resulting stretch. Then, the technique(s) simplify the mesh while respecting the chart boundaries. Next, the parametrization is re-optimized to reduce both stretch and deviation over the whole PM sequence. The charts may then be packed into a texture atlas for improved texture mapping in connection with a parametrization scheme.

A texture atlas scheduling method comprises the following steps of determining basic information for texture streaming scheduling and a data structure; creating the actual physical texture and save the texture loaded into memory; creating an indirect index buffer to store the location information of Mipmap on the physical texture; according to the level of detail information of texture, carrying out the inflow and outflow of texture, and according to the rectangular texture packing algorithm, finding the position information of the current inflow texture on the physical texture; rendering thetexture and relocating the UV coordinates for sampling calculation. The texture atlas scheduling method of the invention is based on a rectangular texture packing algorithm, and effectively reduces the number of DrawCalls by merging texture maps, so that the rendering efficiency is improved. Through the scheduling of textures, the memory usage can be reduced, the necessary texture resources can beloaded gradually, and the memory pressure can be reduced. The invention can effectively reduce the pressure of the graphics processing unit in the rendering process.

A node acquisition unit 11 receives as its input, polygon groups which have a plurality of levels of detail represented in a tree structure and render a model at the plurality of levels of detail, and texture image groups properly assigned to the polygon groups, respectively, and determines nodes corresponding to the texture image groups to be merged. A texture atlas generating unit 12 generates a texture atlas group by merging the texture image groups using information about the nodes the node acquisition unit 11 generates, and converts the texture coordinates of the vertices of the polygon groups while relating the texture coordinates to a drawing position.

Systems and methods for displaying volume data on an arbitrary three-dimensional polygonal surface are disclosed. For each polygon in the polygonal surface, a two-dimensional texture tile is created and these texture tiles are combined to form texture atlases. Each texture atlas is allocated a specific amount of memory in a texture cache. Each polygon in the polygonal surface may be scan-converted and the resulting texels may be placed in the texture cache. Voxels that do not intersect any polygon in the polygonal surface may not be scan-converted. This method may result in reduced use of texture cache.

A node gathering unit (11) has a polygon group and a texture image group as inputs, and determines nodes corresponding to a texture image group to bind. Said polygon group has a relationship represented by multiple detail levels in a tree structure, and expresses a model by means of the multiple detail levels. Each member of said texture image group is allocated uniquely to the polygon group. A texture atlas generation unit (12): uses node information generated by the node gathering unit (11) to bind the texture image group and generate a texture atlas group; and transforms texture coordinates of the vertices of the polygon group, said texture coordinates being transformed in correspondence to drawing positions.

Systems and methods for reducing the amount of texture cache memory needed to store a texture atlas by using uniquely grouped refined triangles to create each texture atlas.

The invention discloses a texture atlas scheduling method. The method comprises the following steps: preprocessing textures needing to be loaded; loading the MipMap level of the texture reservation; the MipMap needing to be scheduled is managed; and carrying out repositioning and texture sampling on the UV. According to the texture atlas scheduling method, map merging can be carried out, the number of Draw Call is effectively reduced, and the rendering efficiency is improved.

A processor-implemented method of generating a three-dimensional (3D) volumetric video with an overlay representing visibility counts per pixel of a texture atlas, associated with a viewer telemetry data is provided. The method includes (i) capturing the viewer telemetry data, (ii) determining a visibility of each pixel in the texture atlas associated with a 3D content based on the viewer telemetry data, (iii) generating at least one visibility counts per pixel of the texture atlas based on the visibility of each pixel in the texture atlas, and (iv) generating one of: the 3D volumetric video with the overlay of at least one heat map associated with the viewer telemetry data, using the at least one visibility counts per pixel and a curated selection of the 3D volumetric content based on the viewer telemetry data, using the visibility counts per pixel.

Position based media pipeline systems and methods for volumetric displays provide content to a volumetric display having at least two pixels arranged in a 3D coordinate space. A three-dimensional (3D) pixel position dataset and a 3D animation are provided and a first volume representation based on the 3D animation is created. A second volume is created based on the first volume and including color data. A texture atlas is assembled based on the second volume and volumetric image data is generated based on the texture atlas. The position based media pipeline outputs the volumetric image data to one or more graphic controllers. The volumetric image data can be output whereby a user can preview the volumetric image data in addition to output to the volumetric display.

A first memory is a main memory that stores a texture image group. A second memory is a VRAM that stores a first texture atlas in which one or more texture images copied from the texture image group are arranged, and a second texture atlas to be newly generated. A texture copy section copies at least one of the texture images arranged in the first texture atlas from the first texture atlas to the second texture atlas.

An exemplary method for simplifying a texture of a three-dimensional model includes simplifying a first three-dimensional model to determine a second three-dimensional model. The first three-dimensional model has a higher resolution than the second three-dimensional model. The method also includes allocating a texture atlas for the second three-dimensional model. The method further includes filling in the texture atlas for the second three-dimensional model. Filling in the texture atlas may include determining a location on the second three-dimensional model corresponding to a pixel in the texture atlas for the second three-dimensional model, determining a location on the first three-dimensional model corresponding to the determined location on the second three-dimensional model, determining a color value texture mapped to the first three-dimensional model at the determined location on the first three-dimensional model, and setting the determined color value to the pixel in the texture atlas for the second three-dimensional model.

The invention relates to the field of artificial intelligence, and discloses a target recognition method, which comprises the steps of obtaining an initial image set, and performing preprocessing operation on the initial image set to obtain a to-be-recognized image set; performing local texture extraction on the to-be-identified image set to obtain a texture atlas set; inputting the texture atlasset into an optimization classifier to execute classification operation, and screening out a target image set from the initial image set according to an obtained classification result; and inputting the target image set into a pre-trained image recognition model for target recognition, and outputting a target recognition result. According to the invention, the problems of low overall process efficiency and computing resource waste of target recognition can be solved.

Position based media pipeline systems and methods for volumetric displays provide content to a volumetric display having at least two pixels arranged in a 3D coordinate space. A three-dimensional (3D) pixel position dataset and a 3D animation are provided and a first volume representation based on the 3D animation is created. A second volume is created based on the first volume and including color data. A texture atlas is assembled based on the second volume and volumetric image data is generated based on the texture atlas. The position based media pipeline outputs the volumetric image data to one or more graphic controllers. The volumetric image data can be output whereby a user can preview the volumetric image data in addition to output to the volumetric display.

Systems and methods are provided for optimizing the geometric stretch of a parametrization scheme. Given an arbitrary mesh, the systems and methods construct a progressive mesh (PM) such that all meshes in the PM sequence share a common texture parametrization. The systems and methods minimize geometric stretch, i.e., small texture distances mapped onto large surface distances, to balance sampling rates over all locations and directions on the surface. The systems and methods also minimize texture deviation, i.e., “slippage” error based on parametric correspondence, to obtain accurate textured mesh approximations. The technique(s) begin by partitioning the mesh into charts using planarity and compactness heuristics. Then, the technique(s) proceed by creating a stretch-minimizing parametrization within each chart, and by resizing the charts based on the resulting stretch. Then, the technique(s) simplify the mesh while respecting the chart boundaries. Next, the parametrization is re-optimized to reduce both stretch and deviation over the whole PM sequence. The charts may then be packed into a texture atlas for improved texture mapping in connection with a parametrization scheme.

The invention relates to a method for tracking the movement of a target in the body by adopting magnetic resonance imaging. The method can be applied to radiotherapy equipment guided by magnetic resonance imaging. The method comprises a process (figure 1) of realizing tracking for the movement of the target in the body, a process (figure 5) of performing similarity comparison on a real-time imageand a texture atlas and methods applied in the two processes, wherein the methods comprise a method (102) of segmenting a target three-dimensional model from an image, a method of calculating a center(3) of a three-dimensional target (2), a method (103) of building a target fault texture atlas, a method (104) of performing real-time imaging on a region of interest and a method (105) of performingsimilarity comparison on a real-time image and the texture atlas.

The invention discloses a texture and normal library construction method based on an artificial intelligence technology. The texture and normal library construction method comprises the steps of obtaining a first original face texture map set; generating a first sampling face texture map set according to the first original face texture map set; for the target face area, determining a first principal component analysis parameter according to the first sampling face texture map set; for the target face area, if the face texture and normal library construction conditions are met, using the firstprincipal component analysis parameter as a texture normal base corresponding to the target face area in the face texture and normal library, wherein the face texture and normal library further comprises (K1) a texture normal base corresponding to the face area. The embodiment of the invention further provides a texture and normal graph generation method and device, a new human face texture and normal library can be constructed, the human face texture graph with low definition can be restored into the ultrahigh-definition human face texture graph by using the human face texture and normal library, and expression of the human face texture graph is enhanced.

Embodiments are described for a method for processing textures for a mesh comprising quadrilateral polygons for real-time rendering of an object or model in a graphics processing unit (GPU), comprising associating an independent texture map with each face of the mesh to produce a plurality of face textures, packing the plurality of face textures into a single texture atlas, wherein the atlas is divided into a plurality of blocks based on a resolution of the face textures, adding a border to the texture map for each face comprising additional texels including at least border texels from an adjacent face texture map, and performing linear interpolation of a trilinear filtering operation on the face textures to resolve resolution discrepancies caused when crossing an edge of a polygon.

Provided are a texture atlas generation unit (10) that generates a texture atlas (41) by combining a plurality of textures, and generates position information (32), in the texture atlas (41), of a texture to be rendered; a polygon information storage unit (330) that stores polygon information (33) in which are set vertex coordinates of the polygon in an output image (42) and vertex texture coordinates corresponding to the vertex coordinates in an image to be rendered on the polygon on the basis of the texture to be rendered; a pixel coordinate calculation unit (22) that detects locations of pixels to be filled in with the polygon in the output image (42), and calculates pixel-corresponding texture coordinates corresponding to locations of pixels in a rendered image; and a coordinate conversion unit (23) that converts the pixel-corresponding texture coordinates to coordinates within an area of the texture to be rendered on the texture atlas (41).

Mesh-based raw video data (or 3D video data) includes a sequence of frames, each of which includes geometry data (e.g., triangle meshes or other meshes) and texture map(s) defining one or more objects. The raw 3D video data is segmented based on consistent mesh topology across frames. For each segment, a consistent mesh sequence (CMS) is defined and a consistent texture atlas (CTA) is generated. The CMS and CTA for each segment are compressed and stored as compressed data files. The compressed data files can be decompressed and used to render displayable images.

The present application discloses a method, device, and system for rending images. The method includes obtaining, by one or more processors, image data comprised in a data frame to be rendered, determining, by the one or more processors, one or more dimensions for a texture atlas based at least in part on the dimensions of the obtained image data, creating, by the one or more processors, the texture atlas based at least in part on the determined dimensions, and rendering, by the one or more processors, the data frame based at least in part on the texture atlas.

A texture atlas scheduling method, comprising the following steps: determining basic information and data structures for texture streaming scheduling; creating an actual physical texture and saving the texture loaded into memory; creating an indirect index buffer and saving the Mipmap in the Position information on the physical texture; according to the level of detail information of the texture, the inflow and outflow of the texture are carried out, and according to the rectangular texture packing algorithm, the position information of the currently inflowing texture is found on the physical texture; the texture is rendered and the UV is repositioned Coordinate for sampling calculation. The texture atlas scheduling method of the present invention is based on the rectangular texture packing algorithm, and by merging the textures, the number of DrawCalls is effectively reduced, so that the rendering efficiency is improved; through the texture scheduling, the memory usage can be reduced, and the progressive loading can be performed. The necessary texture resources reduce memory pressure; it can effectively reduce the pressure on the graphics processing unit during the rendering process.