ÇѱÛÁ¦¸ñ(Korean Title) |
GANs(Generative Adversarial Networks)¸¦ È°¿ëÇÑ ¸ð¼Çĸó À̹ÌÁöÀÇ hole-filling ±â¹ý ¿¬±¸ |
¿µ¹®Á¦¸ñ(English Title) |
Study on hole-filling technique of motion capture images using GANs (Generative Adversarial Networks) |
ÀúÀÚ(Author) |
½Å±¤¼º
½Å¼ºÀ±
Kwang-Seong Shin
Seong-Yoon Shin
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 23 NO. 01 PP. 0160 ~ 0161 (2019. 05) |
Çѱ۳»¿ë (Korean Abstract) |
3Â÷¿ø °´Ã¼¸¦ ¸ðµ¨¸µ Çϱâ À§ÇÑ ¹æ¹ýÀ¸·Î 3D ½ºÄ³³Ê¸¦ ÀÌ¿ëÇÏ´Â ¹æ¹ý°ú ¸ð¼Çĸó ½Ã½ºÅÛÀ» ÀÌ¿ëÇÏ´Â ¹æ¹ý ±×¸®°í Å°³ØÆ®(Kinect) ½Ã½ºÅÛÀ» ÀÌ¿ëÇÏ´Â ¹æ¹ý µîÀÌ ÀÖ´Ù. ÀÌ·¯ÇÑ ¹æ¹ýÀ» ÅëÇØ 3Â÷¿ø °´Ã¼¸¦ »ý¼ºÇÏ´Â °úÁ¤¿¡¼ °¡·ÁÁü¿¡ ÀÇÇØ ÃÔ¿µµÇÁö ¾Ê´Â ºÎºÐÀÌ ¹ß»ýÇÑ´Ù. ¿Ïº®ÇÑ 3Â÷¿ø °´Ã¼¸¦ ±¸ÇöÇϱâ À§Çؼ´Â °¡·ÁÁø ºÎºÐÀ» ÀÓÀǷΠä¿öÁà¾ß ÇÏ´Â »óȲÀÌ ¹ß»ýÇÑ´Ù. ´Ù¾çÇÑ ¿µ»óó¸® ¹æ¹ýÀ» ÅëÇØ °¡Á®Á® ÃÔ¿µµÇÁö ¾ÊÀº ºÎºÐÀ» ¸Þ¿ì´Â ±â¹ýÀÌ Á¸ÀçÇÑ´Ù. º» ¿¬±¸¿¡¼´Â º¸´Ù ÀÚ¿¬½º·¯¿î hole fillingÀ» À§ÇÑ ¹æ¹ýÀ¸·Î ºñÁöµµ±â°èÇнÀÀÇ ÃֽŠƮ·»µåÀÎ GANs¸¦ ÀÌ¿ëÇÑ ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. |
¿µ¹®³»¿ë (English Abstract) |
As a method for modeling a three-dimensional object, there are a method using a 3D scanner, a method using a motion capture system, and a method using a Kinect system. Through this method, a portion that is not captured due to occlusion occurs in the process of creating a three-dimensional object. In order to implement a perfect three-dimensional object, it is necessary to arbitrarily fill the obscured part. There is a technique to fill the unexposed part by various image processing methods. In this study, we propose a method using GANs, which is the latest trend of unsupervised machine learning, as a method for more natural hole-filling. |
Å°¿öµå(Keyword) |
gans
hole-filling
±â°èÇнÀ
ºñÁöµµÇнÀ
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|