专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2015132635A1 DATA SPECULATION FOR ARRAY PROCESSORS 审中-公开
标题翻译：阵列处理器的数据参数
公开(公告)号：WO2015132635A1
公开(公告)日：2015-09-11
申请号：PCT/IB2014/059535
申请日：2014-03-07
申请人： SONY CORPORATION , RASMUSSON, Jim , JONSSON, Håkan , GUSTAVSSON, Jonas , ISBERG, Anders
发明人： RASMUSSON, Jim , JONSSON, Håkan , GUSTAVSSON, Jonas , ISBERG, Anders
IPC分类号： G06F9/38
CPC分类号： G06F15/80 , G06F9/3832 , G06F9/3887
摘要： A method is disclosed of utilizing a plurality of Arithmetic Logic Units (ALUs) of an array processor. It is determined that a first quantity of the ALUs are scheduled to execute a function during a given processing cycle, with each ALU being scheduled to use a respective one of a plurality of selected input vectors as an input. It is also determined that a second quantity of the ALUs are not scheduled for use during the given processing cycle. A plurality of predicted future input vectors that differ from the plurality of selected input vectors are determined. The second quantity of ALUs are scheduled to execute the function during the given processing cycle using respective ones of the plurality of predicted future input vectors as inputs. After completion of the processing cycle, function outputs received from the first and second quantity of ALUs are cached.
摘要翻译：公开了利用阵列处理器的多个算术逻辑单元（ALU）的方法。确定第一数量的ALU被调度为在给定处理周期期间执行功能，其中每个ALU被调度为使用多个选择的输入向量中的相应一个作为输入。还确定在给定处理周期期间第二数量的ALU不被安排用于使用。确定与多个选择的输入向量不同的多个预测未来输入向量。第二数量的ALU被调度为在给定处理周期期间使用多个预测未来输入向量中的相应的输入向量来执行该功能作为输入。在处理周期完成后，从第一和第二数量的ALU接收的功能输出被缓存。

2. 发明申请

WO2015114410A1 OPTIMIZED METHOD FOR ESTIMATING THE DOMINANT GRADIENT DIRECTION OF A DIGITAL IMAGE AREA 审中-公开
标题翻译：用于估计数字图像区域的主要梯度方向的优化方法
公开(公告)号：WO2015114410A1
公开(公告)日：2015-08-06
申请号：PCT/IB2014/058718
申请日：2014-01-31
申请人： SONY CORPORATION , MÅRTENSSON, Linus , GUSTAVSSON, Jonas , RASMUSSON, Jim
发明人： MÅRTENSSON, Linus , GUSTAVSSON, Jonas , RASMUSSON, Jim
IPC分类号： G06T7/00
CPC分类号： G06T5/002 , G06T7/13 , G06T2207/10004 , G06T2207/20192
摘要： The solution disclosed herein reduces the amount of time and computational resources necessary to determine a dominant gradient direction of an image area comprising a plurality of pixels of an image. To that end, the dominant gradient direction of an image area is determined based on two gradient magnitudes determined from four sample points in the image area, where a direction of one of the gradient magnitudes is perpendicular to a direction of the other of the gradient magnitudes. The dominant gradient direction is then determined by taking the arctangent of the computed gradient magnitudes.
摘要翻译：本文公开的解决方案减少了确定包括图像的多个像素的图像区域的主要梯度方向所需的时间量和计算资源。为此，基于从图像区域中的四个采样点确定的两个梯度幅度来确定图像区域的主梯度方向，其中梯度幅度之一的方向垂直于梯度幅度中的另一个的方向。然后通过采用计算的梯度幅度的反正切来确定主梯度方向。

3. 发明申请

WO2015124962A1 TRANSPARENCY DETERMINATION FOR OVERLAYING IMAGES ON AN ELECTRONIC DISPLAY 审中-公开
标题翻译：用于在电子显示器上覆盖图像的透明度确定
公开(公告)号：WO2015124962A1
公开(公告)日：2015-08-27
申请号：PCT/IB2014/059078
申请日：2014-02-18
申请人： SONY CORPORATION , RASMUSSON, Jim
发明人： RASMUSSON, Jim
IPC分类号： G06T19/00 , G06K9/46 , G06T7/00 , G06T11/60
CPC分类号： G06T19/006 , G06K9/00671 , G06K9/4671 , G06T11/00 , G06T2210/62
摘要： According to a computer-implemented method of overlaying two images on an electronic display, and an overlay area between a base image and an overlaid image is determined. A number of feature points in the overlay area of the base image is determined, and a number of feature points in the overlay area of the overlaid image is also determined. A comparison is performed of the number of feature points in the overlay area of each of the base image and the overlaid image. A transparency value is determined for the overlaid image based on the comparison. The base image and overlaid image are displayed on an electronic display, such that the overlaid image is overlaid on the base image, with a transparency of the overlaid image being based on the determined transparency value.
摘要翻译：根据计算机实现的在电子显示器上重叠两个图像的方法，并且确定基本图像和重叠图像之间的覆盖区域。确定基本图像的重叠区域中的多个特征点，并且还确定重叠图像的重叠区域中的多个特征点。对每个基本图像和重叠图像的重叠区域中的特征点的数量进行比较。基于比较确定覆盖图像的透明度值。基本图像和叠加图像被显示在电子显示器上，使得重叠的图像被覆盖在基本图像上，重叠图像的透明度基于所确定的透明度值。

4. 发明申请

WO2011126424A1 TEXTURE COMPRESSION AND DECOMPRESSION 审中-公开
标题翻译：纹理压缩和分解
公开(公告)号：WO2011126424A1
公开(公告)日：2011-10-13
申请号：PCT/SE2011/050145
申请日：2011-02-09
申请人： TELEFONAKTIEBOLAGET L M ERICSSON (publ) , RASMUSSON, Jim , DOGGETT, Michael , STRÖM, Jacob , WENNERSTEN, Per
发明人： RASMUSSON, Jim , DOGGETT, Michael , STRÖM, Jacob , WENNERSTEN, Per
IPC分类号： G06T9/00 , H04N7/26
CPC分类号： G06T9/00
摘要： Embodiments relate to compression and decompression of textures. A texel block (10) is compressed by specifying two major directions in the texel block (10) and defining the profiles of how the texel values change along the respective directions. The resulting compressed texel block (30) comprises two value codewords (31, 32), two line codewords (35-38) and a function codeword (33, 34). The two value codewords (31, 32) are employed to calculate two texel values for the texel block (10). The line codewords (35-38) are employed to determine equations of two lines (20, 22) coinciding with the two major directions in the texel block (10). Signed distances are calculated for each texel (12) from the texel position in the texel block (10) and to the two lines (20, 22). The signed distances are input to a function defined by the function codeword (33, 34) to output two values from which weights are calculated and applied to the two texel values in order to get a representation of the texel value of a texel (12).
摘要翻译：实施例涉及纹理的压缩和解压缩。通过在纹素块（10）中指定两个主要方向来压缩纹理块（10），并且定义纹理值沿着各个方向如何变化的轮廓。所得到的压缩纹理块（30）包括两个值码字（31,32），两行码字（35-38）和一个功能码字（33,34）。两个值码字（31,32）用于计算纹素块（10）的两个纹素值。行码字（35-38）用于确定与纹理块（10）中的两个主要方向一致的两条线（20,22）的等式。从纹理块（10）中的纹素位置和两条线（20,22）中的每个纹理像素（12）计算签名距离。有符号距离被输入到由功能代码字（33,34）定义的函数，以输出计算权重的两个值并将其应用于两个纹素值，以便获得纹素的纹理值的表示（12）。

5. 发明申请

WO2009150004A1 INDEX-BASED PIXEL BLOCK PROCESSING 审中-公开
标题翻译：基于索引的像素块处理
公开(公告)号：WO2009150004A1
公开(公告)日：2009-12-17
申请号：PCT/EP2009/055758
申请日：2009-05-13
申请人： TELEFONAKTIEBOLAGET L M ERICSSON (PUBL) , RASMUSSON, Jim , AKENINE-MÖLLER, Tomas
发明人： RASMUSSON, Jim , AKENINE-MÖLLER, Tomas
IPC分类号： G06T9/00 , H04N7/34
CPC分类号： H04N19/98 , G06T9/004 , H04N19/105 , H04N19/126 , H04N19/14 , H04N19/176 , H04N19/46 , H04N19/593 , H04N19/91
摘要： A pixel block (300) is compressed by determining a reference set of multiple reference property values (10-14). A value index associated with a reference property value of the reference set is assigned to each pixel (310-316) in the pixel block (300) based on the original property value of the pixel (310-316). A prediction of the value index is provided based on the value index assigned to at least one neighboring pixel (314, 316) in the pixel block (300). A prediction error is calculated based on the value index assigned to a pixel (316) and its value index prediction. The compressed pixel block (400) comprises encoded representations (424) of the prediction errors and an encoded representation (410) of the reference set.
摘要翻译：通过确定多个参考属性值（10-14）的参考集来压缩像素块（300）。基于像素（310-316）的原始属性值，将与参考集的参考属性值相关联的值索引分配给像素块（300）中的每个像素（310-316）。基于分配给像素块（300）中的至少一个相邻像素（314,316）的值索引来提供值索引的预测。基于分配给像素（316）的值索引及其值索引预测来计算预测误差。压缩像素块（400）包括预测误差的编码表示（424）和参考集合的编码表示（410）。

6. 发明申请

WO2008122536A2 FRAME BUFFER COMPRESSION AND DECOMPRESSION METHOD FOR GRAPHICS RENDERING 审中-公开
标题翻译：用于图形渲染的框架缓冲器压缩和解压缩方法
公开(公告)号：WO2008122536A2
公开(公告)日：2008-10-16
申请号：PCT/EP2008/053810
申请日：2008-03-31
申请人： TELEFONAKTIEBOLAGET LM ERICSSON (publ) , RASMUSSON, Jim , AKENINE-MÖLLER, Tomas , HASSELGREN, Jon , MUNKBERG, Jacob
发明人： RASMUSSON, Jim , AKENINE-MÖLLER, Tomas , HASSELGREN, Jon , MUNKBERG, Jacob
CPC分类号： G06T11/40 , G09G5/363 , G09G5/393 , G09G2340/02 , G09G2340/10 , H04N19/12 , H04N19/147 , H04N19/154 , H04N19/176 , H04N19/40 , H04N19/423
摘要： Methods and apparatus are disclosed for the processing of frame buffer data, such as color buffer data, in graphics processing applications. Although more generally applicable, these methods and apparatus are particularly useful in real-time, polygon-based, 3D rendering applications. An exemplary method for processing graphics data according to one or more embodiments of the invention begins with the retrieval, from a buffer, of pixel values corresponding to a tile of two or more pixels, and with the updating of one or more of those updated pixel values. The updated pixel values are selectively compressed using a lossy compression operation or a lossless compression operation, based on an accumulated error metric value for the tile. If lossy compression is used, then the accumulated error metric value for the tile is updated; in either event, the compressed pixel values are stored in the frame buffer for further processing. With this approach, the accumulated error caused by successive, or tandem, compression operations may be limited to a pre-determined maximum.
摘要翻译：公开了用于在图形处理应用中处理帧缓冲器数据（例如彩色缓冲器数据）的方法和装置。尽管更普遍适用，但是这些方法和装置在实时，基于多边形的3D渲染应用中特别有用。根据本发明的一个或多个实施例的用于处理图形数据的示例性方法开始于从缓冲器检索对应于两个或更多个像素的图块的像素值，并且随着更新这些更新像素中的一个或多个值。基于瓦片的累积误差度量值，使用有损压缩操作或无损压缩操作来选择性地压缩更新的像素值。如果使用有损压缩，则更新瓦片的累积误差量度值; 在任一情况下，将压缩像素值存储在帧缓冲器中用于进一步处理。利用这种方法，由连续或串联的压缩操作引起的累积误差可能被限制为预定的最大值。

7. 发明申请

WO2009093947A1 PIXEL BLOCK PROCESSING 审中-公开
标题翻译：像素块处理
公开(公告)号：WO2009093947A1
公开(公告)日：2009-07-30
申请号：PCT/SE2008/051038
申请日：2008-09-17
申请人： TELEFONAKTIEBOLAGET LM ERICSSON (publ) , STRÖM, Jacob , AKENINE-MÖLLER, Tomas , WENNERSTEN, Per , RASMUSSON, Jim
发明人： STRÖM, Jacob , AKENINE-MÖLLER, Tomas , WENNERSTEN, Per , RASMUSSON, Jim
IPC分类号： H04N7/26 , G06T9/00
CPC分类号： G06T9/00 , H04N19/105 , H04N19/124 , H04N19/14 , H04N19/15 , H04N19/152 , H04N19/176 , H04N19/182 , H04N19/186 , H04N19/192 , H04N19/426 , H04N19/46 , H04N19/593 , H04N19/98
摘要： A pixel block (300) is losslessly compressed into a candidate compressed block. If the bit length of the candidate block exceeds a threshold value, the property values of the pixels (310-317) in the block (300) are quantized and the quantized values are losslessly compressed into a new candidate compressed block. The procedure is repeated until a candidate compressed block having good image quality and a bit length below the threshold value is found. A compressed representation (400) of the block (300) is determined based on the found candidate compressed block (420) and an identifier (410) of the used quantization parameter.
摘要翻译：像素块（300）被无损压缩成候选压缩块。如果候选块的比特长度超过阈值，则对块（300）中的像素（310-317）的属性值进行量化，并将量化值无损压缩为新的候选压缩块。重复该过程，直到找到具有良好图像质量和位长度低于阈值的候选压缩块。基于所找到的候选压缩块（420）和使用的量化参数的标识符（410）来确定块（300）的压缩表示（400）。

8. 发明申请

WO2012136280A1 A METHOD AND AN ARRANGEMENT FOR TEXTURE COMPRESSION 审中-公开
标题翻译：一种用于纹理压缩的方法和装置
公开(公告)号：WO2012136280A1
公开(公告)日：2012-10-11
申请号：PCT/EP2011/064528
申请日：2011-08-24
申请人： TELEFONAKTIEBOLAGET L M ERICSSON (publ) , STRÖM, Jacob , RASMUSSON, Jim
发明人： STRÖM, Jacob , RASMUSSON, Jim
IPC分类号： G06T9/00 , H04N7/26 , H04N7/34
CPC分类号： G06T9/00 , G06T9/004 , H04N19/126 , H04N19/154 , H04N19/176 , H04N19/593
摘要： The embodiments of the present invention reduce the compression time in order to achieve a faster texture compression. That is achieved by guessing, i.e. estimating the best table or tables (e.g. from tables 0 to 7) representing luminance information, and to only execute the compression for the table(s) estimated to provide the best luminance information.
摘要翻译：本发明的实施例减小了压缩时间，以便实现更快的纹理压缩。这是通过猜测，即估计表示亮度信息的最佳表或表（例如从表0到7）来实现的，并且仅对被估计提供最佳亮度信息的表执行压缩。

9. 发明申请

WO2010029008A1 GRAPHICS-PROCESSING ARCHITECTURE BASED ON APPROXIMATE RENDERING 审中-公开
标题翻译：基于近似渲染的图形处理架构
公开(公告)号：WO2010029008A1
公开(公告)日：2010-03-18
申请号：PCT/EP2009/061391
申请日：2009-09-03
申请人： TELEFONAKTIEBOLAGET L M ERICSSON (PUBL) , RASMUSSON, Jim , AKENINE-MÖLLER, Tomas , HASSELGREN, Jon , MUNKBERG, Jacob , CLARBERG, Petrik
发明人： RASMUSSON, Jim , AKENINE-MÖLLER, Tomas , HASSELGREN, Jon , MUNKBERG, Jacob , CLARBERG, Petrik
IPC分类号： G06T15/00
CPC分类号： G06T15/005
摘要： A graphics processing circuit for rendering three-dimensional graphics data is disclosed. The circuit includes pipelined graphics processing stages, wherein each of two or more of the stages is configured to process at least one of graphics primitives, vertices, tiles, and pixels, according to a stage-specific error budget. Depending on its error budget, each of these stages may select a high- or low-precision calculation, select between lossless and lossy compression, adjust the compression ratio of a variable lossy compression algorithm, or some combination of these approaches. The circuit further comprises a global error-control unit configured to determine error budgets for each of the two or more stages, based on at least one of error data received from the two or more stages, predetermined scene complexity data, and user-defined error settings, and to assign the error budgets to the graphics processing stages. Corresponding methods for processing graphics data are also disclosed.
摘要翻译：公开了一种用于渲染三维图形数据的图形处理电路。电路包括流水线图形处理阶段，其中两个或多个阶段中的每一个被配置为根据阶段特定的错误预算来处理图形基元，顶点，瓦片和像素中的至少一个。根据其错误预算，这些阶段中的每一个可以选择高精度或低精度的计算，在无损压缩和有损压缩之间进行选择，调整可变有损压缩算法的压缩比，或这些方法的某种组合。该电路还包括全局误差控制单元，其被配置为基于从两个或多个阶段接收到的错误数据，预定场景复杂性数据和用户定义的误差中的至少一个来确定两个或更多个阶段中的每一个的错误预算设置，并将错误预算分配给图形处理阶段。还公开了处理图形数据的相应方法。

10. 发明申请

WO2009080448A1 UNIFIED COMPRESSION/DECOMPRESSION GRAPHICS ARCHITECTURE 审中-公开
标题翻译：统一的压缩/解码图形架构
公开(公告)号：WO2009080448A1
公开(公告)日：2009-07-02
申请号：PCT/EP2008/066594
申请日：2008-12-02
申请人： TELEFONAKTIEBOLAGET LM ERICSSON (PUBL) , RASMUSSON, Jim , MUNKBERG, Jacob , HASSELGREN, Jon , CLARBERG, Petrik , AKENINE-MÖLLER, Tomas
发明人： RASMUSSON, Jim , MUNKBERG, Jacob , HASSELGREN, Jon , CLARBERG, Petrik , AKENINE-MÖLLER, Tomas
IPC分类号： G06T15/00
CPC分类号： G06T11/001 , G06T1/60 , G06T9/00 , G06T15/04 , G06T2210/08
摘要： A unified compression/decompression architecture is disclosed for reducing memory bandwidth requirements in 3D graphics processing applications. The techniques described erase several distinctions between a texture (compressed once, and decompressed many times), and buffers (compressed and decompressed repeatedly during rendering of an image). An exemplary method for processing graphics data according to one or more embodiments of the invention thus begins with the updating of one or more tiles of a first image array, which are then compressed, using a real-time buffer compression algorithm, to obtain compressed image array tiles. The compressed image array tiles are stored for subsequent use as a texture. During real-time rendering of a second image array, the compressed image array tiles are retrieved and decompressed using a decompression algorithm corresponding to the buffer compression algorithm. The decompressed image array tiles are then applied as a texture to one or more primitives in the second image array.
摘要翻译：公开了一种用于减少3D图形处理应用中的存储器带宽要求的统一的压缩/解压缩架构。描述的技术擦除纹理（压缩一次，解压缩多次）和缓冲区（在渲染图像期间重复压缩和解压缩）之间的几个区别。因此，根据本发明的一个或多个实施例的用于处理图形数据的示例性方法开始于使用实时缓冲器压缩算法来更新第一图像阵列的一个或多个瓦片，然后将其压缩以获得压缩图像阵列瓦片。压缩的图像阵列瓦片被存储以供随后用作纹理。在第二图像阵列的实时渲染期间，使用对应于缓冲器压缩算法的解压缩算法来检索和解压缩压缩图像阵列瓦片。然后将解压缩的图像阵列瓦片作为纹理应用于第二图像阵列中的一个或多个基元。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式