Netmarble announced on October 10 that Netmarble AI Revolution Center (NARC) and European Conference on Computer Vision (CCV) won second place at COCO DensePose Challenge. The top spot went to Beijing Post University in China.
COCO DensePose Challenge, which was held in Muchen, Germany in last September, is a competition that announces technologies that uses deep learning to recognize images of people and map them to 3D images of the human body for poses. (DensePose)
In particular, the challenge focused on instance segmentation, human key point recognition, and detection of objects using DensePose.
Netmarble had a good result by announcing a model in which Deep Learning recognizes major objects more accurately and in detail.
Netmarble decided that it was difficult to detect a person with a smaller size due to low resolution of Feature Map during the process of DensePose's recognition and prediction.
To solve this problem, Netmarble composed feature maps of different layers of different resolution and stacked the Up-Sampling layer tightly. Up-Sampling is the conversion of low-resolution images to high-resolution images by increasing pixels.
"The technology can be used throughout game art by modeling character pose in 2D images and applying texture," said Ahn Soo-nam, head of NARC game development AI team who participated in this challenge.