US 12,307,572 B2
Apparatus and method for generating 3D object texture map, and recording medium storing instructions to perform method for generating 3D object texture map
Junyong Noh, Daejeon (KR); Sihun Cha, Daejeon (KR); Kwanggyoon Seo, Daejeon (KR); and Amirsaman Ashtari, Daejeon (KR)
Assigned to Korea Advanced Institute of Science and Technology, Daejeon (KR)
Filed by Korea Advanced Institute of Science and Technology, Daejeon (KR)
Filed on Feb. 17, 2023, as Appl. No. 18/170,589.
Claims priority of application No. 10-2022-0157618 (KR), filed on Nov. 22, 2022.
Prior Publication US 2024/0169651 A1, May 23, 2024
Int. Cl. G06T 15/04 (2011.01); G06T 5/50 (2006.01); G06T 7/68 (2017.01); G06T 11/00 (2006.01); G06T 11/60 (2006.01); G06V 10/24 (2022.01); G06V 10/74 (2022.01)
CPC G06T 15/04 (2013.01) [G06T 5/50 (2013.01); G06T 7/68 (2017.01); G06T 11/001 (2013.01); G06T 11/60 (2013.01); G06V 10/24 (2022.01); G06V 10/761 (2022.01); G06T 2207/20221 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A 3D object texture map generation apparatus, comprising:
a memory; and
a processor,
wherein the processor is configured to:
generate a partial texture image by mapping object information in an input image into a texture space;
obtain a sampling image by inputting the partial texture image to a sampler network trained according to a training partial texture image, an aligned partial image in which the training partial texture image is aligned in the texture space, and an augmented partial image augmented from the aligned partial image;
obtain a blending mask and a refined image by inputting the sampling image to a refiner network; and
generate a 3D object texture map by blending the sampling image and the refined image based on the blending mask, and
wherein the sampler network is trained by using the aligned partial image in a first predetermined training interval, using the augmented partial image in a second training interval immediately after the first training interval, and using the training partial texture image and the augmented partial image according to a predetermined ratio in a third training interval immediately after the second training interval.