-
公开(公告)号：US11386293B2
公开(公告)日：2022-07-12
申请号：US17063414
申请日：2020-10-05
Applicant: Intel Corporation
Inventor： Aleksandar Sutic , Zoran Zivkovic , Gilad Michael
Abstract: In an example method for training image signal processors, a reconstructed image is generated via an image signal processor based on a sensor image. An intermediate loss function is generated based on a comparison of an output of one or more corresponding layers of a computer vision network and a copy of the computer vision network. The output of the computer vision network is based on the reconstructed image. An image signal processor is trained based on the intermediate loss function.
-
2.发明申请公开(公告)号：US20200074691A1
公开(公告)日：2020-03-05
申请号：US16674512
申请日：2019-11-05
Applicant: INTEL CORPORATION
Inventor： Masayoshi Asama , Furkan Isikdogan , Sushma Rao , Avi Kalderon , Chyuan-Tyng Wu , Bhavin Nayak , Joao Peralta Moreira , Pavel Kounitsky , Ben Berlin , Gilad Michael
Abstract: An example apparatus for processing images includes a hybrid infinite impulse response—finite impulse response (IIR-FIR) convolution block to receive an image and generate processed image information. The hybrid IIR-FIR convolution block includes a vertical infinite impulse response (IIR) component to approximate a vertical convolution when processing the image.
-
3.发明申请公开(公告)号：US20190130208A1
公开(公告)日：2019-05-02
申请号：US16232715
申请日：2018-12-26
Applicant: Intel Corporation
Inventor： Gilad Michael , Sushma Rao
Abstract: Techniques related to computer vision tasks are discussed. Such techniques include applying a pretrained non-linear transform and pretrained details boosting factor to generate an enhanced image from an input image and reducing the bit depth of the enhanced image prior to applying a pretrained computer vision network to perform the computer vision task.
-
公开(公告)号：US10210180B2
公开(公告)日：2019-02-19
申请号：US14959304
申请日：2015-12-04
Applicant: Intel Corporation
Inventor： Hila Barel , Gilad Michael , Hadas Dahan
Abstract: Techniques related to approximate nearest neighbor searching are discussed. Such techniques may include traversing an approximate nearest neighbor search tree from root node to a resultant leaf node while maintaining a priority queue of best matches, determining candidate entries for evaluation based on the resultant leaf node, and generating search results based on the priority queue and the candidate entries.
-
公开(公告)号：US09697796B2
公开(公告)日：2017-07-04
申请号：US14669269
申请日：2015-03-26
Applicant: Intel Corporation
Inventor： Nir Darshan , Gilad Michael , German Voronov
CPC classification number: G09G5/028 , G06T3/40 , G09G5/393 , G09G2300/0452 , G09G2320/0242 , G09G2360/08 , G09G2360/127 , G09G2360/18 , H04N1/465
Abstract: Techniques related to generating downscaled image or image frame data in a luma chroma separated color space for an image or video pipeline architecture are discussed. Such techniques may include converting input image data to the luma chroma separated color space based on adaptive color coefficients determined based on an illumination indicator associated with the input image data and storing downscaled color converted image data to an input image buffer of the image or video pipeline.
-
Patent Agency Ranking
6.发明授权Non-local means image denoising with detail preservation using self-similarity driven blending 有权非本地意味着使用自相似驱动混合的具有细节保存的图像去噪公开(公告)号：US09489720B2
公开(公告)日：2016-11-08
申请号：US14494163
申请日：2014-09-23
Applicant: Intel Corporation
Inventor： Shaul Oron , Gilad Michael
Abstract: System, apparatus, method, and computer readable media for texture enhanced non-local means (NLM) image denoising. In embodiments, detail is preserved in filtered image data through a blending between the noisy input target pixel value and the NLM pixel value that is driven by self-similarity and further informed by an independent measure of local texture. In embodiments, the blending is driven by one or more blending weight or coefficient that is indicative of texture so that the level of detail preserved by the enhanced noise reduction filter scales with the amount of texture. Embodiments herein may thereby denoise regions of an image that lack significant texture (i.e. are smooth) more aggressively than more highly textured regions. In further embodiments, the blending coefficient is further determined based on similarity scores of candidate patches with the number of those scores considered being based on the texture score.
Abstract translation: 用于纹理增强的非本地装置（NLM）图像去噪的系统，装置，方法和计算机可读介质。 在实施例中，通过在噪声输入目标像素值和由自相似性驱动的NLM像素值之间进行混合，并通过局部纹理的独立测量进一步通知，滤波图像数据中的细节被保留。 在实施例中，混合由指示纹理的一个或多个混合权重或系数驱动，使得由增强噪声降低滤波器保留的细节水平随纹理量而变化。 因此，这里的实施例可以比较高纹理化区域更积极地去除缺乏显着纹理（即平滑）的图像区域。 在另外的实施例中，基于候选补片的相似性得分进一步确定混合系数，其中考虑的那些分数的数量基于纹理得分。
-
公开(公告)号：US11868892B2
公开(公告)日：2024-01-09
申请号：US17887359
申请日：2022-08-12
Applicant: INTEL CORPORATION
Inventor： Furkan Isikdogan , Bhavin V. Nayak , Joao Peralta Moreira , Chyuan-Tyng Wu , Gilad Michael
IPC: G06N3/08 , G06V10/70 , G06V10/764 , G06N3/063 , G06F18/214 , G06N3/048 , G06V10/774 , G06V10/776 , G06V10/82
CPC classification number: G06N3/08 , G06F18/214 , G06N3/048 , G06N3/063 , G06V10/70 , G06V10/764 , G06V10/774 , G06V10/776 , G06V10/82
Abstract: An apparatus to facilitate partially-frozen neural networks for efficient computer vision systems is disclosed. The apparatus includes a frozen core to store fixed weights of a machine learning model, one or more trainable cores coupled to the frozen core, the one or more trainable cores comprising multipliers for trainable weights of the machine learning model, and wherein the alpha blending layer includes a trainable alpha blending parameter, and wherein the trainable alpha blending parameter is a function of a trainable parameter, a sigmoid function, and outputs of frozen and trainable blocks in a preceding layer of the machine learning model.
-
公开(公告)号：US10296605B2
公开(公告)日：2019-05-21
申请号：US14968164
申请日：2015-12-14
Applicant: INTEL CORPORATION
Inventor： Hila Barel , Gilad Michael , Edmond Chalom
Abstract: Techniques related to generating dictionaries for example based image processing algorithms are discussed. Such techniques may include iteratively performing example based image processing for candidate look up entries of candidate pairs from a training set database using a current dictionary to determine a test result for each of the look up entries of the candidate pairs and selecting one or more of the candidate pairs for entry in a resultant dictionary based on an error between the test result and a predetermined result entry for the candidate pairs.
-
公开(公告)号：US20160284314A1
公开(公告)日：2016-09-29
申请号：US14669269
申请日：2015-03-26
Applicant: Intel Corporation
Inventor： Nir Darshan , Gilad Michael , German Voronov
CPC classification number: G09G5/028 , G06T3/40 , G09G5/393 , G09G2300/0452 , G09G2320/0242 , G09G2360/08 , G09G2360/127 , G09G2360/18 , H04N1/465
Abstract: Techniques related to generating downscaled image or image frame data in a luma chroma separated color space for an image or video pipeline architecture are discussed. Such techniques may include converting input image data to the luma chroma separated color space based on adaptive color coefficients determined based on an illumination indicator associated with the input image data and storing downscaled color converted image data to an input image buffer of the image or video pipeline.
Abstract translation: 讨论了与用于图像或视频流水线架构的亮度分色色空间中生成缩小图像或图像帧数据有关的技术。 这样的技术可以包括基于与输入图像数据相关联的照明指示符确定的自适应颜色系数将输入图像数据转换为亮度色度分离的颜色空间，并将缩小的颜色转换的图像数据存储到图像或视频流水线的输入图像缓冲器 。
-
公开(公告)号：US20160179514A1
公开(公告)日：2016-06-23
申请号：US14578605
申请日：2014-12-22
Applicant: Intel Corporation
Inventor： Shaul Oron , Gilad Michael
CPC classification number: G06F9/3001 , G06F7/5306 , G06F9/30036 , G06F9/3004 , G06F9/3017 , G06F9/3822 , G06F9/3851 , G06F9/3855 , G06F9/3877 , G06F9/3887 , G06F9/455 , G06F9/4552
Abstract: A processor includes a front end including a decoder, an execution unit including a shift-sum multiplier (SSM), and a retirement unit. The decoder includes logic identify a multiplication instruction to multiply a first number and a second number. The execution unit includes logic to, based on the instruction, access a look-up table based on the second number to determine a plurality of shift parameters and one or more flag parameters. The SSM includes logic to use the shift parameters to shift the first number to determine a plurality of partial products, and the flag parameters to determine signs of the partial products. The SSM also includes logic to sum the partial products to yield a result of the multiplication instruction.
Abstract translation: 处理器包括前端，包括解码器，包括移位和乘法器（SSM）的执行单元和退出单元。 解码器包括逻辑，识别乘法指令以乘以第一数和第二数。 执行单元包括基于指令访问基于第二数目的查找表以确定多个移位参数和一个或多个标志参数的逻辑。 SSM包括使用移位参数来移动第一数字以确定多个部分乘积的逻辑，以及用于确定部分乘积的符号的标志参数的逻辑。 SSM还包括对部分乘积求和以产生乘法指令的结果的逻辑。
-
-
-
-
-
-
-
-
-
Search Results
30
records
(took 0.028 seconds)
