公开(公告)号：US11587271B2

公开(公告)日：2023-02-21

申请号：US17008964

申请日：2020-09-01

Applicant: Amazon Technologies, Inc.

Inventor： Assaf Neuberger ,  Alexander Lorbert ,  Arik Poznanski ,  Eduard Oks ,  Sharon Alpert ,  Bar Hilleli

IPC: G06T5/50 ,  G06T11/60 ,  G06V40/10 ,  G06K9/62 ,  G06T5/00 ,  G06T7/00 ,  G06T11/00

Abstract: First image data representing a first human wearing a first article of clothing may be received. The first image data, when rendered on a display, may include a first photometric artifact. A first generator network may be used to generate second image data from the first image data. The first photometric artifact may be removed from the second image data. A second generator network may be used to generate third image data from the second image data, the third image data representing the first human in a different pose relative to the first image data. Fourth image data representing the first article of clothing segmented from the first human may be generated and displayed on a display.

公开(公告)号：US12169859B1

公开(公告)日：2024-12-17

申请号：US17533903

申请日：2021-11-23

Applicant: Amazon Technologies, Inc.

Inventor： Alexander Lorbert ,  David Neiman ,  Arik Poznanski ,  Eduard Oks ,  Megan E Anderson ,  Layne Skullerud

IPC: G06Q30/00 ,  G06F16/9535 ,  G06Q30/0601

Abstract: Techniques are generally described for displaying outfit recommendations using a recurrent neural network. In various examples, a computing device may receive a first state vector representing an outfit comprising at least one fashion item. First image data depicting a second fashion item of a first item category may be received. A recurrent neural network may generate a first output feature vector based on the first state vector, the first image data, a first attribute vector, and the first item category. The first output feature vector may be compared to other feature vectors representing other fashion items in the first category to determine distances between the first output feature vector and the other feature vectors. A set of fashion items may be recommended and displayed based on the distances between the first output feature vector and the other feature vectors.

公开(公告)号：US12056911B1

公开(公告)日：2024-08-06

申请号：US17486140

申请日：2021-09-27

Applicant: Amazon Technologies, Inc.

Inventor： Gabi Shalev ,  Alexander Lorbert ,  David Neiman ,  Arik Poznanski ,  Eduard Oks

IPC: G06V10/40 ,  G06F16/2457 ,  G06F16/55 ,  G06F16/56 ,  G06F16/9535 ,  G06F18/22 ,  G06N3/08 ,  G06Q30/06 ,  G06V10/75

CPC classification number: G06V10/40 ,  G06F16/24578 ,  G06F16/55 ,  G06F16/56 ,  G06F16/9535 ,  G06F18/22 ,  G06N3/08 ,  G06Q30/06 ,  G06V10/751

Abstract: Techniques are generally described for performing outfit recommendation using a recurrent neural network. In various examples, a computing device may receive a first state vector representing an outfit comprising at least one fashion item. First image data depicting a second fashion item of a first item category may be received. A machine learning mode may generate a first output feature vector based on the first state vector, the first image data, a first attribute vector, and the first item category. The first output feature vector may be compared to other feature vectors representing other fashion items in the first category to determine distances between the first output feature vector and the other feature vectors. A set of fashion items may be recommended based on the distances between the first output feature vector and the other feature vectors.

公开(公告)号：US20220067994A1

公开(公告)日：2022-03-03

申请号：US17008964

申请日：2020-09-01

Applicant: Amazon Technologies, Inc.

Inventor： Assaf Neuberger ,  Alexander Lorbert ,  Arik Poznanski ,  Eduard Oks ,  Sharon Alpert ,  Bar Hilleli

IPC: G06T11/60 ,  G06K9/62 ,  G06K9/00 ,  G06T7/00 ,  G06T11/00 ,  G06T5/00 ,  G06T5/50

Abstract: Devices and techniques are generally described for catalog normalization and segmentation for fashion images. First image data representing a first human wearing a first article of clothing may be received. The first image data, when rendered on a display, may include a first photometric artifact. A first generator network may be used to generate second image data from the first image data. The first photometric artifact may be removed from the second image data. A second generator network may be used to generate third image data from the second image data, the third image data representing the first human in a different pose relative to the first image data. Fourth image data representing the first article of clothing segmented from the first human may be generated and displayed on a display.