公开(公告)号：US20230095237A1

公开(公告)日：2023-03-30

申请号：US17820203

申请日：2022-08-16

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Joonsoo Kim ,  Tien Cheng Bau ,  Hrishikesh Deepak Garud ,  Kamal Jnawali

IPC: G06T5/00 ,  G06T5/50 ,  G06T7/33 ,  G06T7/246

Abstract: One embodiment provides a method comprising receiving an input video comprising low-resolution (LR) frames and corresponding super-resolution (SR) frames, and generating a motion-compensated previous SR frame based on a current LR frame of the video and a motion-compensated previous residual frame of the video. The previous SR frame aligns with a current SR frame corresponding to the current LR frame. The method further comprises, in response to determining there is a mismatch between the previous SR frame and the current SR frame, correcting in the current SR frame errors that result from motion compensation based on the motion-compensated previous SR frame. The method further comprises restoring details to the current SR frame that were lost as a result of the correcting, and suppressing flickers of the current SR frame on the frequency domain, resulting in a flicker-suppressed current SR frame for presentation on a display.

公开(公告)号：US20230081128A1

公开(公告)日：2023-03-16

申请号：US17879647

申请日：2022-08-02

Applicant: Samsung Electronics Co., Ltd.

Inventor： Tien C. Bau ,  Hrishikesh Deepak Garud

IPC: G06T7/11 ,  G06T3/40

Abstract: A method includes training a semantic segmentation network to generate semantic segmentation maps having class-wise probability values. The method also includes generating a semantic segmentation map using the trained semantic segmentation network. The method further includes utilizing the semantic segmentation map during training of an image generation network as part of a loss function that includes multiple losses. The semantic segmentation network may be trained to be sensitive to picture quality of an output image generated by the image generation network during the training of the image generation network such that increased degradation of the picture quality of the output image results in decreased prediction confidence by the semantic segmentation network. The semantic segmentation network may be trained to vary the class-wise probability values based on the picture quality.

公开(公告)号：US20230153625A1

公开(公告)日：2023-05-18

申请号：US18052297

申请日：2022-11-03

Applicant: Samsung Electronics Co., Ltd.

Inventor： Tien C. Bau ,  Arshita Gupta ,  Hrishikesh Deepak Garud

IPC: G06N3/082

CPC classification number: G06N3/082

Abstract: A method includes accessing a machine learning model, the machine learning model trained using a torque-based constraint. The method also includes receiving an input from an input source and providing the input to the machine learning model. The method also includes receiving an output from the machine learning model. The method also includes instructing at least one action based on the output from the machine learning model. Training the machine learning model includes applying a torque-based constraint on one or more filters of the machine learning model, adjusting, based on applying the torque-based constraint, a first set of one or more filters of the machine learning model to have a higher concentration of weights than a second set of one or more filters of the machine learning model, and pruning at least one channel of the machine learning model based on an average weight for the at least one channel.