US 12,131,482 B2
Learning apparatus, foreground region estimation apparatus, learning method, foreground region estimation method, and program
Ayaka Nakatani, Chiba (JP); Hidehiko Morisada, Tokyo (JP); and Takayuki Shinohara, Tokyo (JP)
Assigned to SONY INTERACTIVE ENTERTAINMENT INC., Tokyo (JP)
Appl. No. 17/288,235
Filed by SONY INTERACTIVE ENTERTAINMENT INC., Tokyo (JP)
PCT Filed Sep. 17, 2019, PCT No. PCT/JP2019/036431
§ 371(c)(1), (2) Date Apr. 23, 2021,
PCT Pub. No. WO2020/110432, PCT Pub. Date Jun. 4, 2020.
Claims priority of application No. PCT/JP2018/043375 (WO), filed on Nov. 26, 2018.
Prior Publication US 2021/0350547 A1, Nov. 11, 2021
Int. Cl. G06T 7/194 (2017.01); G06N 20/00 (2019.01); G06T 7/90 (2017.01); G06V 10/82 (2022.01); G06V 40/10 (2022.01)
CPC G06T 7/194 (2017.01) [G06N 20/00 (2019.01); G06T 7/90 (2017.01); G06V 10/82 (2022.01); G06V 40/10 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/10152 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20212 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A learning apparatus comprising:
processing circuitry configured to
acquire a combination of a first input image representing a background and a foreground and a second input image representing the background in a mode different from that in the first input image, wherein the different mode includes a case where a position or a shape of an item included in the background is different;
acquire a combination of the common first input image and each of a plurality of second input images to which different image processing methods have been applied including setting different gamma values or adding different noises to one image representing the background in a mode different from that in the first input image; and
generate estimation data indicating the foreground region in the first input image in response to input of the first input image and the second input image, and conduct learning based on a given teacher image and the estimation data that is generated in response to inputting the first input image and the second input image.