US 11,776,184 B2
Sky replacement
Jianming Zhang, Campbell, CA (US); Alan Erickson, Franktown, CO (US); I-Ming Pao, Palo Alto, CA (US); Guotong Feng, San Jose, CA (US); Kalyan Sunkavalli, San Jose, CA (US); Frederick Mandia, San Jose, CA (US); Hyunghwan Byun, San Francisco, CA (US); Betty Leong, Los Altos, CA (US); Meredith Payne Stotzner, San Jose, CA (US); Yukie Takahashi, Newark, CA (US); Quynn Megan Le, Morgan Hill, CA (US); and Sarah Kong, Cupertino, CA (US)
Assigned to ADOBE, INC., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Mar. 17, 2021, as Appl. No. 17/204,638.
Claims priority of provisional application 63/093,237, filed on Oct. 18, 2020.
Prior Publication US 2022/0301243 A1, Sep. 22, 2022
Prior Publication US 2023/0005197 A9, Jan. 5, 2023
Int. Cl. G06T 11/60 (2006.01); G06F 3/04842 (2022.01); G06F 3/04845 (2022.01); G06T 11/00 (2006.01)
CPC G06T 11/60 (2013.01) [G06F 3/04842 (2013.01); G06F 3/04845 (2013.01); G06T 11/001 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
generating a plurality of region masks based on a first image using a same mask generation network, wherein the plurality of region masks include a first region mask and a second region mask, and wherein the first region mask corresponds to a same semantically related region of the first image as the first region mask and has a more gradual mask boundary than the second region mask;
generating a defringing layer by combining the first region mask of the plurality of region masks with grayscale version of a second image;
generating a region-specific layer by combining the second region mask of the plurality of region masks with the second image; and
generating a composite image by combining a plurality of layers including the first image, the defringing layer, and the region-specific layer, wherein the composite image is generated based on a first user input to adjust the plurality of layers locally and a second user input to adjust the plurality of layers globally.