-
公开(公告)号：US20230410266A1
公开(公告)日：2023-12-21
申请号：US18200998
申请日：2023-05-23
Applicant: Intel Corporation
Inventor： Furkan Isikdogan , Timo Gerasimow , Gilad Michael
IPC: G06T5/00 , G06T3/00 , G06T5/20 , G06T7/73 , G06V40/18 , G06F18/214 , G06F18/21 , G06V10/764 , G06V10/82 , G06V10/44 , G06V10/98
CPC classification number: G06T5/006 , G06T3/0093 , G06T5/20 , G06T7/73 , G06V40/193 , G06F18/214 , G06F18/217 , G06V10/764 , G06V10/82 , G06V10/454 , G06V10/98 , G06T2210/44 , G06T2207/30041
Abstract: An example apparatus for adjusting eye gaze in images one or more processors to execute instructions to bidirectionally train a neural network; access a target angle and an input image, the input image including an eye in a first position; generate a vector field with the neural network; and generate a gaze-adjusted image based on the vector field, the gaze-adjusted image including the eye in a second position.
-
公开(公告)号：US20220391680A1
公开(公告)日：2022-12-08
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
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：US10796200B2
公开(公告)日：2020-10-06
申请号：US15965158
申请日：2018-04-27
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.
-
公开(公告)号：US20200293870A1
公开(公告)日：2020-09-17
申请号：US16886103
申请日：2020-05-28
Applicant: Intel Corporation
Inventor： Furkan Isikdogan , Bhavin V. Nayak , Joao Peralta Moreira , Chyuan-Tyng Wu , Gilad Michael
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：US20190050682A1
公开(公告)日：2019-02-14
申请号：US15965158
申请日：2018-04-27
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.
-
Patent Agency Ranking
公开(公告)号：US11409986B2
公开(公告)日：2022-08-09
申请号：US16232336
申请日：2018-12-26
Applicant: INTEL CORPORATION
Inventor： Chaitanya R. Gandra , Chyuan-Tyng Wu , Gilad Michael , Liron Ain-Kedem , Leo Isikdogan
Abstract: An example apparatus for processing images includes a trainable vision scaler to receive an image. The trainable vision scaler is to generate output including a feature map or an enhanced image based on the image. The trainable vision scaler is to transmit the output to a computer vision network. The computer vision network is trained to perform a computer vision task using the output.
-
公开(公告)号：US11302035B2
公开(公告)日：2022-04-12
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.
-
18.发明授权公开(公告)号：US10755425B2
公开(公告)日：2020-08-25
申请号：US16116318
申请日：2018-08-29
Applicant: Intel Corporation
Inventor： Jun Nishimura , Timo Gerasimow , Sushma Rao , Chyuan-Tyng Wu , Aleksandar Sutic , Gilad Michael
Abstract: A mechanism is described for facilitating automatic tuning of image signal processors using reference images in image processing environments, according to one embodiment. A method of embodiments, as described herein, includes one or more processors to: receive images associated with one or more scenes captured by one or more cameras; access tuning parameters associated with functionalities within an image signal processor (ISP) pipeline; generate reference images based on the tuning parameters, wherein a reference image is associated with an image for each functionality within the ISP pipeline; and automatically tune the ISP pipeline based on selection of one or more of the reference images for one or more of the images for one or more of the functionalities.
-
19.发明申请公开(公告)号：US20200226429A1
公开(公告)日：2020-07-16
申请号：US16833263
申请日：2020-03-27
Applicant: Intel Corporation
Inventor： Avi Kalderon , Gilad Michael , Joao Peralta Moreira , Bhavin Nayak , Furkan Isikdogan
Abstract: An apparatus, method, and a computer readable medium for attenuating visual artifacts in processed images. An annotated dataset of images to be processed by an image processing system is created. An adversarial control network is trained to operate as an image quality expert in classifying images. After the adversarial control network has been trained, the adversarial control network is used to supervise the image processing system on-the-fly.
-
公开(公告)号：US20170169057A1
公开(公告)日：2017-06-15
申请号：US14968164
申请日：2015-12-14
Applicant: INTEL CORPORATION
Inventor： Hila Barel , Gilad Michael , Edmond Chalom
CPC classification number: G06F17/30277 , G06K9/00 , G06K9/228 , G06K9/4642 , G06K9/4652 , G06K9/6223 , G06K9/6255 , G06K9/6807 , G06N99/005 , G06T3/4015
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.
-
-
-
-
-
-
-
-
-
Search Results
30
records
(took 0.013 seconds)
