	US 12,205,238 B2
	Automatic dolly zoom image processing device
Chih-Wei Chen, Hsinchu (TW); Pei-Kuei Tsung, Hsinchu (TW); Yao-Sheng Wang, Hsinchu (TW); Chun Chen Lin, Hsinchu (TW); and Chia-Ching Lin, Hsinchu (TW)
Assigned to MediaTek Inc., Hsinchu (TW)
Filed by MediaTek Inc., Hsinchu (TW)
Filed on Apr. 18, 2022, as Appl. No. 17/722,771.
Claims priority of provisional application 63/186,198, filed on May 10, 2021.
Prior Publication US 2022/0358619 A1, Nov. 10, 2022
Int. Cl. G06K 9/00 (2022.01); G06T 3/04 (2024.01); G06T 3/40 (2006.01); G06T 5/50 (2006.01); G06T 5/77 (2024.01); G06T 7/11 (2017.01); G06T 7/194 (2017.01); G06T 7/50 (2017.01); G06T 7/55 (2017.01); G06T 11/00 (2006.01); H04N 5/272 (2006.01)

CPC G06T 3/40 (2013.01) [G06T 3/04 (2024.01); G06T 5/50 (2013.01); G06T 5/77 (2024.01); G06T 7/11 (2017.01); G06T 7/194 (2017.01); G06T 7/50 (2017.01); G06T 7/55 (2017.01); G06T 11/00 (2013.01); H04N 5/272 (2013.01); G06T 2200/24 (2013.01); G06T 2207/10004 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)]

20 Claims

1. A method for producing a dolly zoom effect, comprising:

capturing a main image at a main location, the main image including at least a foreground object of a given size and a background;

calculating one or more side view locations based on a zoom-in factor to be applied to the background and an estimated size of the foreground object;

guiding a user to capture one or more side view images at the one or more side view locations;

superimposing the foreground object of the given size onto a zoomed-in background; and

performing image inpainting using side view information from the one or more side view images.