公开(公告)号：US20240014233A1

公开(公告)日：2024-01-11

申请号：US18470847

申请日：2023-09-20

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Zilu YANG ,  Xuanwu YIN ,  Guo LI ,  Yamin SUN ,  Wenming ZUO ,  Yunlong ZHAN ,  Xiandou ZHANG

IPC: H01L27/146 ,  H04N25/13

CPC classification number: H01L27/14621 ,  H04N25/13

Abstract: An image sensor includes a pixel array and a color filter array covering the pixel array, where the color filter array includes a plurality of color filter elements, the plurality of color filter elements include at least one first color filter element and at least one second color filter element, each first color filter element includes a basic color filter and an extended color filter, and each second color filter element includes a plurality of basic color filters. A color of the extended color filter is different from a color of the basic color filter. An optical signal passing through the basic color filter is at least for imaging, and an optical signal passing through the extended color filter is for spectral measurement.

公开(公告)号：US20240146868A1

公开(公告)日：2024-05-02

申请号：US18390243

申请日：2023-12-20

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Ziyang ZHANG ,  Weihua HE ,  Chen YANG ,  Jianxing LIAO ,  Kun TIAN ,  Ying WANG ,  Yunlong ZHAN

IPC: H04N7/01 ,  G06T5/50 ,  G06T7/20 ,  G06V20/40

CPC classification number: H04N7/0135 ,  G06T5/50 ,  G06T7/20 ,  G06V20/44 ,  G06T2207/20221

Abstract: Embodiments of this disclosure relate to the multimedia processing field, and provide a video frame interpolation method, apparatus, and a device. In the video frame interpolation method in this disclosure, a first image at first time, a second image at second time, and sensor data captured by a dynamic vision sensor apparatus are obtained, and the sensor data includes dynamic event data between the first time and the second time. At least one target image is determined based on the first image, the second image, and the sensor data, where the at least one target image is an image corresponding to at least one target time between the first time and the second time. The dynamic event data is used to help compensate for motion information missing from existing image data. This implements accurate prediction of an intermediate image, and improves image prediction effect.