公开(公告)号：US12094079B2

公开(公告)日：2024-09-17

申请号：US17658706

申请日：2022-04-11

Applicant: Apple Inc.

Inventor： Feng Li ,  Jia Xue ,  Saeed Izadi

IPC: G06T3/40 ,  G06T3/4046 ,  G06T7/30

CPC classification number: G06T3/4046 ,  G06T7/30 ,  G06T2207/20212

Abstract: Devices, methods, and computer readable media to provide enhanced images in multi-camera systems, e.g., by using images captured by cameras with different optical properties and/or sensors. In one embodiment, the techniques comprise reference-based image super-resolution techniques for producing, with a first neural network employing robust feature aggregation techniques (e.g., techniques able to blend between single-image enhancement and feature aggregation, when appropriate), an enhanced output image that attempts to match the quality characteristics of each of region in a lower quality (e.g., shorter focal length, larger field of view (FOV)) input image with the quality characteristics of the region's determined guidance region from at least a second, i.e., higher quality (e.g., longer focal length, smaller FOV image) input image. The guidance regions from the higher quality image that are determined for each region from the lower quality input image may be determined by performing homographic mapping and/or semantic feature matching techniques.

公开(公告)号：US11688100B1

公开(公告)日：2023-06-27

申请号：US17351869

申请日：2021-06-18

Applicant: Apple Inc.

Inventor： Libin Sun ,  Feng Li ,  Jianping Zhou ,  Xiaoxing Li ,  Jia Xue

IPC: G06T7/80 ,  G06T9/00 ,  G06N3/04 ,  H04N23/62

CPC classification number: G06T7/80 ,  G06N3/04 ,  G06T9/002 ,  H04N23/62

Abstract: Devices, methods, and non-transitory program storage devices are disclosed to provide enhanced images in multi-camera systems, e.g., by using information from images captured by cameras with different properties in terms of optics and/or sensors. In one embodiment, the techniques comprise: obtaining a first image from a first image capture device, wherein the first image has a first field of view (FOV) and a first set of quality characteristics; obtaining a second image from a second image capture device, wherein the second image has a second FOV and a second set of quality characteristics, and wherein the second FOV partially overlaps the first FOV; obtaining a neural network that produces a modified second image having a modified second set of quality characteristics determined by the neural network attempting to match the first set of quality characteristics; and generating an output image based, at least in part, on the modified second image.

公开(公告)号：US20230098437A1

公开(公告)日：2023-03-30

申请号：US17658706

申请日：2022-04-11

Applicant: Apple Inc.

Inventor： Feng Li ,  Jia Xue ,  Saeed Izadi

IPC: G06T3/40 ,  G06T7/30

Abstract: Devices, methods, and computer readable media to provide enhanced images in multi-camera systems, e.g., by using images captured by cameras with different optical properties and/or sensors. In one embodiment, the techniques comprise reference-based image super-resolution techniques for producing, with a first neural network employing robust feature aggregation techniques (e.g., techniques able to blend between single-image enhancement and feature aggregation, when appropriate), an enhanced output image that attempts to match the quality characteristics of each of region in a lower quality (e.g., shorter focal length, larger field of view (FOV)) input image with the quality characteristics of the region's determined guidance region from at least a second, i.e., higher quality (e.g., longer focal length, smaller FOV image) input image. The guidance regions from the higher quality image that are determined for each region from the lower quality input image may be determined by performing homographic mapping and/or semantic feature matching techniques.