公开(公告)号：US20210319326A1

公开(公告)日：2021-10-14

申请号：US16886429

申请日：2020-05-28

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yoo Jin Choi ,  Jongha Ryu ,  Mostafa El-Khamy ,  Jungwon Lee ,  Young-Han Kim

IPC: G06N3/08 ,  G06N3/04

Abstract: A system and method for operating a neural network. In some embodiments, the neural network includes a variational autoencoder, and the training of the neural network includes training the variational autoencoder with a plurality of samples of a first random variable; and a plurality of samples of a second random variable, the plurality of samples of the first random variable and the plurality of samples of the second random variable being unpaired, the training of the neural network including updating weights in the neural network based on a first loss function, the first loss function being based on a measure of deviation from consistency between: a conditional generation path from the first random variable to the second random variable, and a conditional generation path from the second random variable to the first random variable.

公开(公告)号：US20210287342A1

公开(公告)日：2021-09-16

申请号：US17010670

申请日：2020-09-02

Applicant: Samsung Electronics Co., Ltd.

Inventor： Zengli Yang ,  Long Bao ,  Shuangquan Wang ,  Dongwoon Bai ,  Jungwon Lee

IPC: G06T5/00 ,  G06T5/30 ,  G06T5/50 ,  G06N3/08 ,  G06N3/04

Abstract: A method for denoising an image includes: receiving, by a processing circuit of a user equipment, an input image; supplying, by the processing circuit, the input image to a trained convolutional neural network (CNN) including a multi-scale residual dense block (MRDB), the MRDB including: a residual dense block (RDB); and an atrous spatial pyramid pooling (ASPP) module; computing, by the processing circuit, an MRDB output feature map using the MRDB; and computing, by the processing circuit, an output image based on the MRDB output feature map, the output image being a denoised version of the input image.

公开(公告)号：US20210224953A1

公开(公告)日：2021-07-22

申请号：US17223991

申请日：2021-04-06

Applicant: Samsung Electronics Co., Ltd.

Inventor： Mostafa El-Khamy ,  Jungwon Lee ,  Haoyu Ren

IPC: G06T3/40 ,  G06N3/04 ,  G06N3/08

Abstract: In a method for super resolution imaging, the method includes: receiving, by a processor, a low resolution image; generating, by the processor, an intermediate high resolution image having an improved resolution compared to the low resolution image; generating, by the processor, a final high resolution image based on the intermediate high resolution image and the low resolution image; and transmitting, by the processor, the final high resolution image to a display device for display thereby.

公开(公告)号：US10897769B2

公开(公告)日：2021-01-19

申请号：US16267620

申请日：2019-02-05

Applicant: Samsung Electronics Co., Ltd.

Inventor： Mojtaba Rahmati ,  Dongwoon Bai ,  Jungwon Lee

IPC: H04W72/08 ,  H04L1/00 ,  H04L5/00 ,  H04W72/06 ,  H04J11/00

Abstract: A method and an apparatus. The method includes receiving a signal including a serving signal and an interference signal; applying a Gaussian approximation (GA) on the serving signal and the interference signal; determining likelihood metrics for hypotheses on a rank of the interference signal, a precoding matrix index, and power on the GA-applied interference signal based on a covariance matrix for each of the hypotheses; and selecting one of the hypotheses that maximizes one of the likelihood metrics.

公开(公告)号：US10855510B2

公开(公告)日：2020-12-01

申请号：US16270133

申请日：2019-02-07

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyukjoon Kwon ,  Linbo Li ,  Jungwon Lee ,  Sandeep Krishnamurthy

IPC: H04L27/34 ,  H04W72/04 ,  H04L27/18 ,  H04L5/00 ,  H04L1/00

Abstract: Apparatuses, systems, and methods are described concerning a new type of superposition multiplexing transmission constellation (super-constellation): the Gray-mapped Non-uniform-capable Constellation (GNC). Apparatuses, systems, and methods for generating GNC super-constellations are described, as well as apparatuses, systems, and methods for receiving, demapping, and decoding transmissions using GNC super-constellations. Apparatuses, systems, and methods for selecting a type of superposition multiplexing transmission constellation based on various conditions are also described.

公开(公告)号：US10853921B2

公开(公告)日：2020-12-01

申请号：US16362021

申请日：2019-03-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seongjun Park ,  Shuangquan Wang ,  Jungwon Lee

IPC: G06T5/20 ,  G06T5/00 ,  G06T5/50

Abstract: A method and an apparatus are provided for sharpening an image, by an image processor of an electronic device. An input image is received. Low pass filtering is applied to the input image to generate a first image and a second image. A kernel size of first image and the second image are different. Edge preserving filtering is applied to the input image to generate a third image and a fourth image. A kernel size of the third image and the fourth image are different. The first image is subtracted from the third image to obtain a first resulting image. The first image has a larger kernel size than the third image. The second image from the fourth image to obtain a second resulting image. The second image has a larger kernel size than the fourth image. The first resultant image, the second resultant image, and the input image are summed to generate a sharpened image.

公开(公告)号：US10803378B2

公开(公告)日：2020-10-13

申请号：US15655557

申请日：2017-07-20

Applicant: Samsung Electronics Co., Ltd.

Inventor： Haoyu Ren ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: G06N3/04 ,  G06N3/08

Abstract: Apparatuses and methods of manufacturing same, systems, and methods for generating a convolutional neural network (CNN) are described. In one aspect, a minimal CNN having, e.g., three or more layers is trained. Cascade training may be performed on the trained CNN to insert one or more intermediate layers until a training error is less than a threshold. When cascade training is complete, cascade network trimming of the CNN output from the cascade training may be performed to improve computational efficiency. To further reduce network parameters, convolutional filters may be replaced with dilated convolutional filters with the same receptive field, followed by additional training/fine-tuning.

公开(公告)号：US20200312346A1

公开(公告)日：2020-10-01

申请号：US16751094

申请日：2020-01-23

Applicant: Samsung Electronics Co., Ltd.

Inventor： Amin Fazeli ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: G10L21/0232 ,  G06N3/08 ,  H04R3/04 ,  G06N20/10

Abstract: A system for performing echo cancellation includes: a processor configured to: receive a far-end signal; record a microphone signal including: a near-end signal; and an echo signal corresponding to the far-end signal; extract far-end features from the far-end signal; extract microphone features from the microphone signal; compute estimated near-end features by supplying the microphone features and the far-end features to an acoustic echo cancellation module including a recurrent neural network including: an encoder including a plurality of gated recurrent units; and a decoder including a plurality of gated recurrent units; compute an estimated near-end signal from the estimated near-end features; and transmit the estimated near-end signal to the far-end device. The recurrent neural network may include a contextual attention module; and the recurrent neural network may take, as input, a plurality of error features computed based on the far-end features, the microphone features, and acoustic path parameters.

公开(公告)号：US20200250797A1

公开(公告)日：2020-08-06

申请号：US16362021

申请日：2019-03-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seongjun Park ,  Shuangquan Wang ,  Jungwon Lee

IPC: G06T5/00 ,  G06T5/50 ,  G06T5/20

Abstract: A method and an apparatus are provided for sharpening an image, by an image processor of an electronic device. An input image is received. Low pass filtering is applied to the input image to generate a first image and a second image. A kernel size of first image and the second image are different. Edge preserving filtering is applied to the input image to generate a third image and a fourth image. A kernel size of the third image and the fourth image are different. The first image is subtracted from the third image to obtain a first resulting image. The first image has a larger kernel size than the third image. The second image from the fourth image to obtain a second resulting image. The second image has a larger kernel size than the fourth image. The first resultant image, the second resultant image, and the input image are summed to generate a sharpened image

公开(公告)号：US20200151237A1

公开(公告)日：2020-05-14

申请号：US16742231

申请日：2020-01-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： Binnan ZHUANG ,  Dongwoon Bai ,  Jungwon Lee

IPC: G06F17/12 ,  H04N5/232 ,  G06T5/00 ,  H04N13/282 ,  G06T7/285 ,  G06T7/80 ,  G06F17/16 ,  G06F7/58 ,  H04N19/00

Abstract: An apparatus and method of low complexity optimization solver for path smoothing with constraint variation are herein disclosed. According to one embodiment, an apparatus includes an L1 central processing unit (CPU) configured to transform an L1 trend filtering problem to a primal-dual linear programming (LP) optimization problem pair; and an L1 arithmetic logic unit (ALU) connected to the L1 CPU and configured to solve a primal problem of the primal-dual LP optimization problem pair with an extended full tableau simplex method.