公开(公告)号：US20230156342A1

公开(公告)日：2023-05-18

申请号：US17566425

申请日：2021-12-30

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Abdullah ABUOLAIM ,  Abhijith PUNNAPPURATH ,  Abdelrahman ABDELHAMED ,  Michael Scott BROWN ,  Aleksai LEVINSHTEIN

IPC: H04N5/235 ,  H04N5/357

CPC classification number: H04N5/2353 ,  H04N5/2354 ,  H04N5/357

Abstract: A method of generating a low-light image is provided. The method includes receiving a raw image, removing an amount of first illumination from the raw image, applying a low exposure condition to the raw image having the amount of first illumination removed, and applying an amount of low-light illumination to the raw image having the applied low exposure condition.

公开(公告)号：US20240071035A1

公开(公告)日：2024-02-29

申请号：US18112822

申请日：2023-02-22

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Stavros TSOGKAS ,  Fengjia ZHANG ,  Aleksai LEVINSHTEIN ,  Allen Douglas JEPSON

IPC: G06V10/26 ,  G06T5/00 ,  G06T7/215 ,  G06T7/254 ,  G06T7/38 ,  G06V10/77 ,  G06V20/40

CPC classification number: G06V10/273 ,  G06T5/005 ,  G06T7/215 ,  G06T7/254 ,  G06T7/38 ,  G06V10/7715 ,  G06V20/46 ,  G06T2207/20221

Abstract: The present disclosure provides methods, apparatuses, and computer-readable mediums for performing multi-frame de-fencing by a device. In some embodiments, a method includes obtaining an image burst having at least one portion of a background scene obstructed by an opaque obstruction. The method further includes generating a plurality of obstruction masks marking the at least one portion of the background scene obstructed by the opaque obstruction in images of the image burst. The method further includes computing a motion of the background scene, with respect to a keyframe selected from the plurality of images, by applying an occlusion-aware optical flow model. The method further includes reconstructing the selected keyframe by providing a combination of features to an image fusion and inpainting network. The method further includes providing, to the user, the reconstructed keyframe comprising an unobstructed version of the background scene of the image burst.

公开(公告)号：US20240144434A1

公开(公告)日：2024-05-02

申请号：US18051707

申请日：2022-11-01

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Aleksai LEVINSHTEIN ,  Allan Douglas Jepson

IPC: G06T5/50 ,  G06V10/44 ,  G06V10/80 ,  G06V10/82 ,  H04N5/14

CPC classification number: G06T5/50 ,  G06V10/44 ,  G06V10/803 ,  G06V10/82 ,  H04N5/145 ,  G06T2207/20221

Abstract: Image alignment is achieved by obtaining a fused optical flow based on a global motion estimate and an optical flow estimate. The fused optical flow may be used to warp the first image and/or the second image into aligned features or aligned images. An output image may then be obtained by combining.

公开(公告)号：US20240303789A1

公开(公告)日：2024-09-12

申请号：US18389072

申请日：2023-11-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ashkan MIRZAEI ,  Tristan TY AUMENTADO-ARMSTRONG ,  Konstantinos G. DERPANIS ,  Igor GILITSCHENSKI ,  Aleksai LEVINSHTEIN ,  Marcus BRUBAKER

IPC: G06T5/00 ,  G06T15/20

CPC classification number: G06T5/77 ,  G06T15/20

Abstract: Provided is a method of training a neural radiance field and producing a rendering of a 3D scene from a novel viewpoint with view-dependent effects. The neural radiance field is initially trained using a first loss associated with a plurality of unmasked regions associated with a reference image and a plurality of target images. The training may also be updated using a second loss associated with a depth estimate of a masked region in the reference image. The training may also be further updated using a third loss associated with a view-substituted image associated with a respective target image. The view-substituted image is a volume rendering from the reference viewpoint across pixels with view-substituted target colors. In some embodiments, the neural radiance field is additionally trained with a fourth loss. The fourth loss is associated with dis-occluded pixels in a target image.

公开(公告)号：US20220138500A1

公开(公告)日：2022-05-05

申请号：US17512312

申请日：2021-10-27

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Aleksai LEVINSHTEIN ,  Xinyu SUN ,  Haicheng WANG ,  Vineeth Subrahmanya BHASKARA ,  Stavros TSOGKAS ,  Allan JEPSON

IPC: G06K9/62 ,  G06T3/40 ,  G06T5/20 ,  G06N3/04 ,  G06N3/08

Abstract: A method for training a super-resolution network may include obtaining a low resolution image; generating, using a first machine learning model, a first high resolution image based on the low resolution image; generating, using a second machine learning model, a second high resolution image based on the first high resolution image and an unpaired dataset of high resolution images; obtaining a training data set using the low resolution image and the second high resolution image; and training the super-resolution network using the training data set.

公开(公告)号：US20250069321A1

公开(公告)日：2025-02-27

申请号：US18800919

申请日：2024-08-12

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Tristan AUMENTADO-ARMSTRONG ,  Ashkan MIRZAEI ,  Aleksai LEVINSHTEIN ,  Marcus Anthony BRUBAKER ,  Konstantinos G. DERPANIS ,  Igor GILITSCHENSKI

IPC: G06T15/20 ,  G06T15/06

Abstract: An electronic device includes: a camera; a memory; a processor to obtain a plurality of multiview color images of the object; obtain, from the latent field about the object, a plurality of multiview latent images and a plurality of camera parameters respectively corresponding to the plurality of multiview latent images; based on the plurality of multiview latent images and the plurality of camera parameters, render a first feature map about the object by using a latent field and an autoencoder; based on the first feature map about the object, train the improved NeRF by performing iterative operations; receive a request for a novel view of the object; generate, by using the improved NeRF, a second feature map from the novel view of the object; and generate, by a decoder of the autoencoder, an image about the novel view of the object based on the second feature map.

公开(公告)号：US20240153046A1

公开(公告)日：2024-05-09

申请号：US18228472

申请日：2023-07-31

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ashkan MIRZAEI ,  Ttistan TY AUMENTADO-ARMSTRONG ,  Konstantinos G. DERPANIS ,  Marcus A. BRUBAKER ,  Igor GILITSCHENSKI ,  Aleksai LEVINSHTEIN

IPC: G06T5/00 ,  G06T7/11 ,  G06V10/774 ,  G06V10/82 ,  G06V10/94 ,  G06V20/40

CPC classification number: G06T5/005 ,  G06T7/11 ,  G06V10/774 ,  G06V10/82 ,  G06V10/945 ,  G06V20/49 ,  G06T2200/04 ,  G06T2200/24 ,  G06T2207/10021 ,  G06T2207/10028 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20092

Abstract: A computer-implemented method of configuring an electronic device for inpainting source three-dimensional (3D) scenes, includes: receiving the source 3D scenes and a user's input about a first object of the source 3D scenes; generating accurate object masks about the first object of the source 3D scenes; and generating inpainted 3D scenes of the source 3D scenes by using an inpainting neural radiance field (NeRF) based on the accurate object masks.