METHOD AND APPARATUS FOR GENERATING DEPTH MAP, AND STORAGE MEDIUM

(19)

(11)

EP 4 027 299 A8

(12)	CORRECTED EUROPEAN PATENT APPLICATION
	Note: Bibliography reflects the latest situation

(15)	Correction information:
	Corrected version no 1 (W1 A2)

(48)	Corrigendum issued on:
	12.10.2022 Bulletin 2022/41

(88)	Date of publication A3:
	21.09.2022 Bulletin 2022/38

(43)	Date of publication:
	13.07.2022 Bulletin 2022/28

(21)	Application number: 22164198.8

(22)	Date of filing: 24.03.2022

(51)

International Patent Classification (IPC):

G06T 5/00^(2006.01)

G06T 7/50^(2017.01)

(52)	Cooperative Patent Classification (CPC):
	G06T 5/005; G06T 2207/10028; G06T 7/50; G06T 2207/20084

(84)	Designated Contracting States:
	AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
	Designated Extension States:
	BA ME
	Designated Validation States:
	KH MA MD TN

(30)

Priority:

25.03.2021 CN 202110320739

(71)	Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
	Beijing 100085 (CN)

(72)	Inventors:
	JIANG, Minyue Beijing, 100085 (CN) TAN, Xiao Beijing, 100085 (CN) SUN, Hao Beijing, 100085 (CN)

(74)	Representative: advotec.
	Patent- und Rechtsanwaltspartnerschaft Tappe mbB Widenmayerstraße 4 80538 München 80538 München (DE)

(54)	METHOD AND APPARATUS FOR GENERATING DEPTH MAP, AND STORAGE MEDIUM

(57) A method for generating a depth map, an electronic device and a storage medium. The method includes: obtaining (101, 201) a point cloud map and a visual image of a scene; generating (102) a first depth value of each pixel in the visual image based on the point cloud map and the visual image; determining (103, 203) a three-dimensional coordinate location of each pixel in a world coordinate system based on a coordinate location and the first depth value of each pixel in the visual image; generating (104) a second depth value of each pixel by inputting the three-dimensional coordinate location and pixel information of each pixel into a depth correction model; and generating (105, 208) the depth map of the scene based on the second depth value of each pixel.