US 12,425,605 B2
Image in-painting for irregular holes using partial convolutions
Guilin Liu, San Jose, CA (US); Fitsum A. Reda, Santa Clara, CA (US); Kevin Shih, Santa Clara, CA (US); Ting-Chun Wang, San Jose, CA (US); Andrew Tao, Los Altos, CA (US); and Bryan Catanzaro, Sunnyvale, CA (US)
Assigned to NVIDIA Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Mar. 21, 2019, as Appl. No. 16/360,895.
Claims priority of provisional application 62/646,309, filed on Mar. 21, 2018.
Prior Publication US 2019/0295228 A1, Sep. 26, 2019
Int. Cl. G06K 9/00 (2022.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06N 20/10 (2019.01); G06N 20/20 (2019.01); G06T 3/4007 (2024.01); G06T 5/20 (2006.01); G06T 5/77 (2024.01); H04N 19/132 (2014.01); H04N 19/139 (2014.01); H04N 19/172 (2014.01); H04N 19/587 (2014.01)
CPC H04N 19/139 (2014.11) [G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06N 20/10 (2019.01); G06N 20/20 (2019.01); G06T 3/4007 (2013.01); G06T 5/20 (2013.01); G06T 5/77 (2024.01); H04N 19/132 (2014.11); H04N 19/172 (2014.11); H04N 19/587 (2014.11); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
performing, using a neural network, two or more successive partial convolutions using corresponding masks to generate two or more feature maps that successively increase a number of valid pixels used in each respective partial convolution to at least partially fill one or more holes in one or more images.