发明名称 Low-complexity bilateral filter (BF) implementation in a data processing device
摘要 A method includes implementing, through a processor communicatively coupled to a memory and/or a hardware block, a Bilateral Filter (BF) including a spatial filter component and a range filter component, and implementing the spatial filter component with a low-complexity function to allow for focus on the range filter component. The method also includes determining, through the processor, filter tap value(s) related to the range filter component as a function of radiometric distance between a pixel of a video frame and/or an image and other pixels thereof based on a pre-computed corpus of data related to execution of an application in accordance with a filtering requirement of the pixel by the application. Further, the method includes constraining, through the processor, the filter tap value(s) to a form i×base based on the BF implementation. i is an integer and base is a floating point base.
申请公布号 US8983223(B2) 申请公布日期 2015.03.17
申请号 US201313948210 申请日期 2013.07.23
申请人 NVIDIA Corporation 发明人 Avadhanam Niranjan;Sohani Prashant
分类号 G06K9/40;G06T5/00 主分类号 G06K9/40
代理机构 Zilka-Kotab, PC 代理人 Zilka-Kotab, PC
主权项 1. A method comprising: implementing, through at least one of a processor communicatively coupled to a memory and a hardware block, a Bilateral Filter (BF) comprising a spatial filter component and a range filter component; implementing, through the at least one of the processor and the hardware block, the spatial filter component with an appropriate function having reduced complexity compared to a Gaussian function to allow for focus on the range filter component; determining, through the processor, filter tap value(s) related to the range filter component as a function of radiometric distance between a pixel of at least one of a video frame and an image and other pixels thereof based on a pre-computed corpus of data related to execution of an application in accordance with a filtering requirement of the pixel by the application; and constraining, through the processor, the filter tap value(s) to a form i×base to further reduce complexity of filtering of the pixel based on the BF implementation, i being an integer and base being a floating point base.
地址 Santa Clara CA US