公开(公告)号：US20220383530A1

公开(公告)日：2022-12-01

申请号：US17772205

申请日：2020-10-27

Applicant: RAMOT AT TEL-AVIV UNIVERSITY LTD.

Inventor： Raja GIRYES ,  Yotam GIL ,  Shay ELMALEM ,  Harel HAIM

IPC: G06T7/593 ,  G06T7/80

Abstract: A system for depth estimation, comprises at least a first and a second depth estimation optical systems, each configured for receiving a light beam from a scene and estimating depths within the scene, wherein the first system is a monocular depth estimation optical system; and an image processor, configured for receiving depth information from the first and second systems, and generating a depth map or a three-dimensional image of the scene based on the received depth information.

公开(公告)号：US20230375462A1

公开(公告)日：2023-11-23

申请号：US18198354

申请日：2023-05-17

Applicant: Ramot at Tel-Aviv University Ltd.

Inventor： Raja GIRYES ,  Shay Avraham ELMALEM

IPC: G01N21/21 ,  G02B5/02 ,  G02B27/28

CPC classification number: G01N21/21 ,  G02B5/0263 ,  G02B27/288 ,  H04N25/40

Abstract: A system for polarization imaging comprises an optical diffuser characterized by a point spread function (PSF), an image sensor, a spatially multiplexed polarization filter between the optical diffuser and the image sensor, and an image processor. The image processor receives signals from the image sensor and reconstructs, based on the PSF, a separate image for each polarization direction formed on the polarization filter.

公开(公告)号：US20210073959A1

公开(公告)日：2021-03-11

申请号：US16952184

申请日：2020-11-19

Applicant: Ramot at Tel-Aviv University Ltd.

Inventor： Shay ELMALEM ,  Raja GIRYES ,  Harel HAIM ,  Alexander BRONSTEIN ,  Emanuel MAROM

IPC: G06T5/30 ,  G06T5/00 ,  G06T7/50 ,  G06T19/00 ,  G06N3/08

Abstract: A method of designing an element for the manipulation of waves, comprises: accessing a computer readable medium storing a machine learning procedure, having a plurality of learnable weight parameters. A first plurality of the weight parameters corresponds to the element, and a second plurality of the weight parameters correspond to an image processing. The method comprises accessing a computer readable medium storing training imaging data, and training the machine learning procedure on the training imaging data, so as to obtain values for at least the first plurality of the weight parameters.

公开(公告)号：US20210248715A1

公开(公告)日：2021-08-12

申请号：US17243599

申请日：2021-04-29

Applicant: Ramot at Tel-Aviv University Ltd.

Inventor： Eliyahu SCHWARTZ ,  Raja GIRYES ,  Alexander BRONSTEIN

IPC: G06T3/40 ,  G06N3/08 ,  G06N3/04 ,  G06T5/00

Abstract: A method of processing an input image comprises receiving the input image, storing the image in a memory, and accessing, by an image processor, a computer readable medium storing a trained deep learning network. A first part of the deep learning network has convolutional layers providing low-level features extracted from the input image, and convolutional layers providing a residual image. A second part of the deep learning network has convolutional layers for receiving the low-level features and extracting high-level features based on the low-level features. The method feeds the input image to the trained deep learning network, and applies a transformation to the residual image based on the extracted high-level features.

公开(公告)号：US20200234402A1

公开(公告)日：2020-07-23

申请号：US16251123

申请日：2019-01-18

Applicant: Ramot at Tel-Aviv University Ltd.

Inventor： Eliyahu SCHWARTZ ,  Raja GIRYES ,  Alexander BRONSTEIN

IPC: G06T3/40 ,  G06N3/04 ,  G06N3/08 ,  G06T5/00

Abstract: A method of processing an input image comprises receiving the input image, storing the image in a memory, and accessing, by an image processor, a computer readable medium storing a trained deep learning network. A first part of the deep learning network has convolutional layers providing low-level features extracted from the input image, and convolutional layers providing a residual image. A second part of the deep learning network has convolutional layers for receiving the low-level features and extracting high-level features based on the low-level features. The method feeds the input image to the trained deep learning network, and applies a transformation to the residual image based on the extracted high-level features.