-
公开(公告)号：US20240342595A1
公开(公告)日：2024-10-17
申请号：US18615289
申请日：2024-03-25
申请人： Netflix, Inc.
发明人： Gregoire Pean
IPC分类号： A63F13/355 , G06T1/20 , G06T15/80
CPC分类号： A63F13/355 , G06T1/20 , G06T15/80
摘要： The disclosed computer-implemented method includes accessing media frame generation input events produced as part of a multimedia application on a media server, selecting at least one media frame that is to be rendered according to the media frame generation input events, determining graphics processing capabilities of a client device on which the selected media frame is to be rendered, and generating a render command for the selected media frame based on the determined graphics processing capabilities of the client device. The render command includes contextual graphics information and graphics processing unit (GPU) pipeline information for use in rendering the selected media frame on the client device. The method also includes transmitting the generated render command to the client device to initiate rendering of the selected media frame using the contextual graphics information and the GPU pipeline information. Various other methods, systems, and computer-readable media are also disclosed.
-
公开(公告)号：US12112410B2
公开(公告)日：2024-10-08
申请号：US17752458
申请日：2022-05-24
发明人： Casper Van Benthem
CPC分类号： G06T11/40 , G06T1/20 , G06T7/13 , G06T15/005 , G06T15/503 , G06T15/80 , G09G5/363 , G06T2207/20021 , G06T2210/12 , G09G2360/122 , G06T15/005 , G06T11/40 , G06T1/20 , G06T15/80 , G06T7/13 , G06T15/503 , G06T2207/20021 , G06T2210/12 , G09G5/363 , G09G2360/122
摘要： Conservative rasterization hardware comprises hardware logic arranged to perform an edge test calculation for each edge of a primitive and for two corners of each pixel in a microtile. The two corners that are used are selected based on the gradient of the edge and the edge test result for one corner is the inner coverage result and the edge test result for the other corner is the outer coverage result for the pixel. An overall outer coverage result for the pixel and the primitive is calculated by combining the outer coverage results for the pixel and each of the edges of the primitive in an AND gate. The overall inner coverage result for the pixel is calculated in a similar manner.
-
公开(公告)号：US20240312028A1
公开(公告)日：2024-09-19
申请号：US18478271
申请日：2023-09-29
申请人： Intel Corporation
摘要： Described herein, in one embodiment, is computer-implemented method of estimating dense optical flow using primitive ID data comprising generating a primitive ID buffer (e.g., triangle ID buffer) for a frame during rendering, rendering the frame with a unique color for each primitive ID, providing a rendered primitive ID buffer for the current and previous frame along with a confidence buffer and sparse optical flow between frames to a machine learning model, and generating an estimated dense optical flow via the machine learning model based on the input.
-
公开(公告)号：US12079917B2
公开(公告)日：2024-09-03
申请号：US18213609
申请日：2023-06-23
发明人： James Glanville
CPC分类号： G06T15/005 , G06F8/41 , G06F9/30101 , G06T1/60 , G06T15/80 , G09G5/363
摘要： A rendering optimisation identifies a draw call within a current render (which may be the first draw call in the render or a subsequent draw call in the render) and analyses a last shader in the series of shaders used by the draw call to determine whether the last shader samples from the one or more buffers at coordinates matching a current fragment location. If this determination is positive, the method further recompiles the last shader to replace an instruction that reads data from one of the one or more buffers at coordinates matching a current fragment location with an instruction that reads from the one or more buffers at coordinates stored in on-chip registers.
-
公开(公告)号：US12056804B2
公开(公告)日：2024-08-06
申请号：US18317825
申请日：2023-05-15
发明人： Thomas Edwin Frisinger , Richard Hammerstone , Andrew Evan Gruber , Gang Zhong , Yun Du , Jonnala Gadda Nagendra Kumar
CPC分类号： G06T15/005 , G06F9/30101 , G06F9/30123 , G06T1/20 , G06T1/60 , G06T15/80
摘要： This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for fast incremental shared constants. In aspects, a CPU may determine/update shared constant data for a first draw call of a plurality of draw calls. The shared constant data, which may correspond to at least one shader, may be updated based on a draw call update for the first draw call. The CPU may communicate the updated shared constant data for the first draw call to a GPU. The GPU may receive, in at least one register, the updated shared constant data from the CPU and configure the at least one register based on the updated shared constant data corresponding to the draw call update of the first draw call of the plurality of draw calls.
-
公开(公告)号：US20240193868A1
公开(公告)日：2024-06-13
申请号：US18388562
申请日：2023-11-10
发明人： Enrique de Lucas
摘要： A method of rendering a frame showing a scene formed by primitives in a tile-based graphics processing system includes a geometry processing phase tiling the primitives in the scene, to determine which primitives at least partially overlap which tiles of the frame to be rendered. A rendering phase obtains a fragment density map defining one or more texels, each texel corresponding to an area of the frame to be rendered and having an associated fragment size, wherein for each of the texels, the texel's height is an integer multiple of a native tile height used in the tile-based graphics processing system and the texel's width is an integer multiple of a native tile width used in the tile-based graphics processing system. The rendering phase also determines from the fragment density map a fragment size to be used to render the tile, performing sampling using the determined fragment size and performing fragment shading using the determined fragment size.
-
7.发明公开公开(公告)号：US20240135636A1
公开(公告)日：2024-04-25
申请号：US18489050
申请日：2023-10-17
CPC分类号： G06T15/506 , G06F3/12 , G06F3/14 , G06T15/80 , G06V10/141 , G06V10/56 , H04N1/6016
摘要： Image data expressed in a first color space is converted into an expression in a second color space to be used during rendering by using a color conversion profile, and converted image data is generated. A setting related to an application to physically-based rendering is performed on a parameter to be used when performing physically-based rendering on a print medium as a 3D object and related to an appearance of the print medium, the physically-based rendering of a printed print medium on which an input image is printed is performed using the set parameter, and a rendering image corresponding to an appearance of the print medium in a virtual space is displayed in a mode in which a difference in applications of the parameter during rendering is comparable.
-
公开(公告)号：US11955246B2
公开(公告)日：2024-04-09
申请号：US16627171
申请日：2018-06-26
发明人： Pourya Shirazian , Mahdi Azizian
摘要： A method is provided to model a 3D structure comprising: producing a surface mesh representation of the 3D structure; producing a volume mesh representation of the 3D structure based upon the surface mesh; sorting vertices of the volume mesh into a first sub-list that includes only surface vertices and a second sub-list that includes only internal vertices; applying shading to the surface mesh by accessing only surface vertices in the first sub-list; determining deformation of the volume mesh by accessing both surface vertices in the first sub-list and internal vertices in the second sub-list.
-
公开(公告)号：US11948245B2
公开(公告)日：2024-04-02
申请号：US17455167
申请日：2021-11-16
申请人： Apple Inc.
发明人： Shaona Ghosh , Mona Zehni
CPC分类号： G06T15/506 , G06N3/08 , G06T15/80
摘要： Novel machine learning (ML) models are introduced for image reconstruction training and inference workflows, which are able to estimate intrinsic components of single view images, including albedo, normal, and lighting components. According to some embodiments, such models may be trained on a mix of real and synthetic image datasets. For training on real datasets, both reconstruction and cross-relighting consistency terms may be imposed. The use of a cross-relighting consistency term allows for the use of multiple images of the same scene—although lit under different lighting conditions—to be used during training. At inference time, the model is able to operate on single or multiple images. According to other embodiments, adversarial training (e.g., in the form of a generative adversarial network (GAN)) may optionally be incorporated into the training workflow, e.g., in order to better refine the re-rendered images from the individual lighting and geometric components estimated by the model.
-
10.发明公开公开(公告)号：US20240070966A1
公开(公告)日：2024-02-29
申请号：US18387171
申请日：2023-11-06
发明人： Luke T. Peterson , James Jones , Aaron Dwyer
摘要： Graphics processing system configured to perform ray tracing. Rays are bundled together and processed together. When differential data is needed by a shader, the data of a true ray in the bundle can be used rather than processing separate tracker rays.
-
-
-
-
-
-
-
-
-
搜索结果
1360 条记录 (耗时 0.031 秒)
