• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document : 2 / 14 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) Áõ°­Çö½ÇÀ» À§ÇÑ GPU ±â¹Ý ½Ç½Ã°£ ±¤¿ø ÃßÁ¤ ±â¹ý
¿µ¹®Á¦¸ñ(English Title) GPU-Based Real-Time Light Source Estimation for Augmented Reality
ÀúÀÚ(Author) ¹Ú¼Ò¿µ   Á¶¼ºÈÆ   À̼º±æ   Soyoung Park   Sunghun Jo   Sungkil Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 46 NO. 01 PP. 0001 ~ 0008 (2019. 01)
Çѱ۳»¿ë
(Korean Abstract)
»çÀü¿¡ ÃÔ¿µµÈ Á¤ÀûÀÎ ½Ç¼¼°è À̹ÌÁö À§¿¡ °¡»ó ¹°Ã¼¸¦ µ¿ÀûÀ¸·Î ·»´õ¸µÇϱâ À§Çؼ­´Â À̹ÌÁö ¿¡ ³ªÅ¸³­ Á¶¸íȯ°æÀ» ºÐ¼®ÇÏ°í À̸¦ °¡»ó°´Ã¼ ·»´õ¸µ¿¡ ¹Ý¿µÇÏ´Â ±¤ÇÐÀû Á¤ÇÕ °úÁ¤ÀÌ ¿ä±¸µÈ´Ù. ÀÌ¿¡ º» ³í¹®Àº ½Ç¼¼°èÀÇ 3Â÷¿ø º¹¿ø ±âÇÏ¿Í ±×¿¡ ¸ÅÇεǴ ÅؽºÃķκÎÅÍ ±¤¿øÀÇ 3Â÷¿ø À§Ä¡¸¦ ÃßÁ¤ÇÏ´Â ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. ¸ÕÀú ±¤¿øÀÇ ³ôÀº °­µµ¸¦ º¹¿øÇϱâ À§ÇØ LDR·Î ÃÔ¿µµÈ ÅؽºÃĸ¦ HDR·Î º¯È¯ÇÏ°í, °èÃþÀû ºÐ ÇÒÀ» ÅëÇÑ »ùÇøµ ±â¹ýÀ¸·Î 2D À̹ÌÁö »ó¿¡¼­ ±¤¿øÀ» ÃßÁ¤ÇÑ ÈÄ, ±âÇÏ »ó¿¡¼­ÀÇ ´ëÀÀÀ» ÅëÇØ 3Â÷¿ø À§Ä¡ ¸¦ ȹµæÇÑ´Ù. º» ±¤¿ø ÃßÁ¤ ±â¹ýÀº »ùÇøµÀÇ °¢ ´Ü°è¿¡¼­ »ý¼ºµÈ °ÝÀÚ ¿µ¿ªµéÀÇ Á¤º¸¸¦ ¹Ó¸Ê ÅؽºÃÄ¿¡ Àú ÀåÇÔÀ¸·Î½á ¿µ¿ªÀÇ ºÐÇÒÀÌ GPU »ó¿¡¼­ º´·Ä 󸮵ǵµ·Ï ¼³°èµÇ¾î ½Ç½Ã°£ ¼º´ÉÀ» º¸ÀδÙ. º» ±â¹ýÀº ȯ°æ ¸Ê ±â¹ÝÀÇ ·»´õ¸µ°ú ´Þ¸® ±×¸²ÀÚ¿Í °°ÀÌ ±¤¿øÀÇ ¸í½ÃÀû À§Ä¡°¡ ÇÊ¿äÇÑ ·»´õ¸µ¿¡ È¿°úÀûÀ¸·Î ¾²ÀÏ ¼ö ÀÖ´Ù.
¿µ¹®³»¿ë
(English Abstract)
To render synthetic objects on static images captured from the real world, estimation of illumination from the images and application for rendering the objects is solicited. In this work, we propose a real-time estimation of light sources, when the 3D-reconstructed geometry of an indoor scene and the corresponding textures are available. To restore the high intensity of the light source, we first convert an LDR image into HDR. The converted image is then used to get 2D positions of the light sources by hierarchical division-based sampling technique. Lastly, 3D positions of the light sources are estimated from texture-geometry mapping. Since the sampling technique stores grid areas generated at each stage in mipmap textures, the division of areas is processed on GPU in a parallel way, which makes it work in real-time. Our approach can be used in rendering where explicit positions of the light sources are asked, such as shadows.
Å°¿öµå(Keyword) Áõ°­Çö½Ç   ±¤¿ø   ÃßÁ¤   GPU   augmented reality   light sources   estimation  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå