公开(公告)号：US11216917B2

公开(公告)日：2022-01-04

申请号：US16403355

申请日：2019-05-03

Applicant: Amazon Technologies, Inc.

Inventor： Silviu Stefan Andrei ,  Nataliya Shapovalova ,  Walterio Wolfgang Mayol Cuevas

IPC: G06T5/00 ,  G06K9/00

Abstract: Techniques for enhancing an image are described. For example, a lower-resolution image from a video file may be enhanced using a trained neural network applying the trained neural network on the lower-resolution image to remove artifacts by removing artifacts by generating, using a layer of the trained neural network, a residual value based on the proper subset of the received image and at least one corresponding image portion of a preceding lower resolution image in the video file and at least one corresponding image portion of a subsequent lower resolution image in the video file, upscale the lower-resolution image using bilinear upsampling, and combine the upscaled received image and residual value to generate an enhanced image.

公开(公告)号：US11017506B2

公开(公告)日：2021-05-25

申请号：US16403386

申请日：2019-05-03

Applicant: Amazon Technologies, Inc.

Inventor： Walterio Wolfgang Mayol Cuevas ,  Silviu Stefan Andrei ,  Nataliya Shapovalova

IPC: G06T5/00 ,  G06N3/08 ,  G06K9/00 ,  G06N3/04

Abstract: Techniques for enhancing an image are described. For example, a lower-resolution image, for example from a video file, may be enhanced using a trained neural network by applying the trained neural network to enhance a middle lower-resolution image of a plurality of lower-resolution images using a generator with filters of a generative adversary network. In some examples, a plurality of sequential feature processing acts are performed on the lower-resolution images to generate a residual which is added to a filtered version of one of the lower-resolution images to generate an enhanced image.

公开(公告)号：US11741582B1

公开(公告)日：2023-08-29

申请号：US17568497

申请日：2022-01-04

Applicant: Amazon Technologies, Inc.

Inventor： Silviu Stefan Andrei ,  Nataliya Shapovalova ,  Walterio Wolfgang Mayol Cuevas

IPC: G06T5/00 ,  G06V20/10

CPC classification number: G06T5/005 ,  G06V20/10 ,  G06T2207/10016 ,  G06T2207/20192

Abstract: Techniques for enhancing an image are described. For example, a lower-resolution image from a video file may be enhanced using a trained neural network applying the trained neural network on the lower-resolution image to remove artifacts by removing artifacts by generating, using a layer of the trained neural network, a residual value based on the proper subset of the received image and at least one corresponding image portion of a preceding lower resolution image in the video file and at least one corresponding image portion of a subsequent lower resolution image in the video file, upscale the lower-resolution image using bilinear upsampling, and combine the upscaled received image and residual value to generate an enhanced image.

公开(公告)号：US11425448B1

公开(公告)日：2022-08-23

申请号：US17219278

申请日：2021-03-31

Applicant: Amazon Technologies, Inc.

Inventor： Tejas Shamrao Khot ,  Nataliya Shapovalova ,  Silviu Stefan Andrei ,  Walterio Wolfgang Mayol Cuevas ,  Wasiq Bokhari

IPC: H04N21/431 ,  H04N5/783 ,  G06T5/00 ,  H04N21/2662 ,  H04N21/81 ,  H04N21/2343

Abstract: An input video stream corresponding to input video content may be received over one or more networks. The input video stream may include a first image frame. An input visual feature of the first image frame may be matched to a reference visual feature of a reference image. The reference image may have a higher image quality than the first image frame. A replacement visual feature may be generated for the input visual feature. The replacement visual feature may be generated based at least in part on the reference visual feature. An enhanced image frame corresponding to the first image frame may be generated by at least replacing the input visual feature in the first image frame with the replacement visual feature. An enhanced video stream may be provided. The enhanced image frame may be a substitute for the first image frame in the enhanced video stream.

公开(公告)号：US11210769B2

公开(公告)日：2021-12-28

申请号：US16403367

申请日：2019-05-03

Applicant: Amazon Technologies, Inc.

Inventor： Nataliya Shapovalova ,  Walterio Wolfgang Mayol Cuevas ,  Silviu Stefan Andrei

IPC: G06T5/20 ,  G06T5/00 ,  H04N21/2662 ,  G06T7/13 ,  H04N21/2343 ,  G06N3/08

Abstract: Techniques for enhancing an image are described. For example, a lower-resolution image from a video file may be enhanced using a trained neural network applying the trained neural network on the lower-resolution image to remove artifacts by generating, using a layer of the trained neural network, a residual value based on the proper subset of the received image and at least one corresponding image portion of a previously generated higher resolution image in the video file, upscaling the received image using bilinear upsampling, and combining the upscaled received image and residual value to generate an enhanced image.

公开(公告)号：US10949353B1

公开(公告)日：2021-03-16

申请号：US15785166

申请日：2017-10-16

Applicant: Amazon Technologies, Inc.

Inventor： Joseph Patrick Tighe ,  Stephen Gould ,  Vuong Van Le ,  Davide Modolo ,  Nataliya Shapovalova

IPC: G06F13/28 ,  G06F12/0868 ,  G06N20/00

Abstract: A data processing pipeline controller receives a request, from a data iterator associated with a machine learning model, for a data output of a module in the data processing pipeline, wherein each module in the data processing pipeline has an associated cache. The controller determines whether a data output of the module is stored in the associated cache and responsive to the data output being stored in the associated cache, provides the data output from the associated cache to the data iterator without processing data through the module.