US 12,293,533 B2
Depth map image generation method and computing device therefor
Ken Kim, Seoul (KR); Ji Wuck Jung, Goyang-si (KR); Farkhod Rustam Ugli Khudayberganov, Seoul (KR); and Mikhail Li, Paju-si (KR)
Assigned to 3I INC., Daegu (KR)
Filed by 3I INC., Daegu (KR)
Filed on Aug. 1, 2022, as Appl. No. 17/878,206.
Application 17/878,206 is a continuation of application No. PCT/KR2021/012652, filed on Sep. 16, 2021.
Claims priority of application No. 10-2021-0081608 (KR), filed on Jun. 23, 2021; and application No. 10-2021-0081814 (KR), filed on Jun. 23, 2021.
Prior Publication US 2022/0414909 A1, Dec. 29, 2022
Int. Cl. G06K 9/00 (2022.01); G06T 7/55 (2017.01)
CPC G06T 7/55 (2017.01) [G06T 2207/10024 (2013.01); G06T 2207/20084 (2013.01)] 14 Claims
OG exemplary drawing
 
14. A computing device comprising:
a memory configured to store one or more instructions; and
a processor configured to execute the one or more instructions stored in the memory,
wherein the processor executes the one or more instructions:
to receive a basic RGB image and a basic depth map image corresponding to the basic RGB image,
to generate a plurality of learning spherical images from a basic spherical virtual image after changing configuration information of the basic spherical virtual image generated by performing spherical transformation based on the basic RGB image and the basic depth map image,
and to generate a plurality of learning RGB images and a plurality of learning depth map images by performing plane transformation on the plurality of learning spherical images,
wherein the plurality of learning RGB images and the plurality of learning depth map images each match 1:1.