• 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¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) È®Àå ÇÕ¼º°ö ½Å°æ¸Á°ú ÀÚ±â Áöµµ ¼øȯ Àû´ëÀû »ý¼º ½Å°æ¸ÁÀ» ÀÌ¿ëÇÑ ¾È°³ Á¦°Å ³×Æ®¿öÅ©
¿µ¹®Á¦¸ñ(English Title) Unpaired Image Dehazing Network using smoothed Dilated Convolution Network and Self-Supervised CycleGAN
ÀúÀÚ(Author) À̼öµ¿   Ȳ¼±Èñ   ÃÖ¿µ¿ì   º¯Çý¶õ   Soodong Lee   Sunhee Hwang   Yeongwoo Choi   Hyeran Byun  
¿ø¹®¼ö·Ïó(Citation) VOL 26 NO. 02 PP. 0104 ~ 0109 (2020. 02)
Çѱ۳»¿ë
(Korean Abstract)
¾È°³ Á¦°Å ¿¬±¸ÀÇ ¸ñÀûÀº ¾È°³ ¿µ»óÀ» ¾È°³°¡ ¾ø´Â ¿µ»óÀ¸·Î º¹¿ø½ÃÅ°´Â µ¥ ÀÖ´Ù. ´ëºÎºÐÀÇ ¾È°³ Á¦°Å ¿¬±¸´Â ¸ðµ¨ ÇнÀÀ» À§ÇØ µ¿ÀÏÇÑ Àå¸é¿¡ ´ëÇÏ¿© ¾È°³ ¿µ»ó°ú ¾È°³°¡ ¾ø´Â ¿µ»óÀÇ ½ÖÀ¸·Î ÀÌ·ç¾îÁø µ¥ÀÌÅͼÂÀ» ÀÌ¿ëÇÏ¿´´Ù. ÇÏÁö¸¸ ½ÇÁ¦ ȯ°æ¿¡¼­´Â ¾È°³ ¿µ»ó°ú ¾È°³°¡ ¾ø´Â ¿µ»óÀÌ ¿Ïº®È÷ ÀÏÄ¡ÇÏ´Â µ¥ÀÌÅ͸¦ ÃëµæÇϱâ¶õ ºÒ°¡´É¿¡ °¡±õ´Ù. ±×·¡¼­ º» ³í¹®¿¡¼­´Â ½ÖÀ» ÀÌ·çÁö ¾Ê´Â ¾È°³ ¿µ»ó°ú ¾È°³°¡ ¾ø´Â ¿µ»óÀ» ÀÌ¿ëÇÏ¿© ¾È°³ Á¦°Å¸¦ ¼öÇàÇÏ´Â ³×Æ®¿öÅ© °³¹ßÀ» ¸ñÇ¥·Î ÇÑ´Ù. Á¦¾ÈÇÑ ¸ðµ¨Àº ½ÖÀ» ÀÌ·çÁö ¾Ê´Â µ¥ÀÌÅ͸¦ ÀÌ¿ëÇϱâ À§ÇØ ¼øȯ Àû´ëÀû »ý¼º ½Å°æ¸Á ±¸Á¶·Î µÇ¾îÀÖÀ¸¸ç, ¾È°³ Á¦°Å ¼º´ÉÀ» ³ôÀ̱â À§ÇØ È®Àå ÇÕ¼º°ö ½Å°æ¸Á, Áö°¢Àû ¼Õ½Ç ÇÔ¼ö¿Í ÀÚ±â Áöµµ ÇнÀ¹æ¹ý Áß ÇϳªÀΠȸÀü ¼Õ½Ç ÇÔ¼ö·Î ÀÌ·ç¾îÁø ¾È°³ Á¦°Å ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÑ ±â¼úÀÇ °´°üÀûÀÎ ¼º´ÉÆò°¡¸¦ À§ÇØ D-HAZY µ¥ÀÌÅͼ°ú ½ÇÁ¦ ¾È°³ ¿µ»ó¿¡ ´ëÇØ ½ÇÇèÀ» ÁøÇàÇÏ¿´°í Á¤¼ºÀû, Á¤·®ÀûÀÎ °á°ú¸¦ ºÐ¼®ÇÏ¿© Á¦¾ÈÇÑ ¹æ¹ýÀÇ ¼º´ÉÀ» ÀÔÁõÇÏ¿´´Ù
¿µ¹®³»¿ë
(English Abstract)
The purpose of this study is to investigate methods restoring hazy images to haze-free images. Most dehazing studies have used datasets that consist of pairs of images, one hazy and one haze-free of the same scene, for training purposes. However, in the real world, it is almost impossible to acquire this kind of data where the hazy image and the haze-free image are perfectly matched except for the haze. Therefore, this paper aims to develop a network that removes haze using hazy images and images without haze that are not paired. The proposed model uses the CycleGAN architecture with this unpaired data. In order to improve the haze removal performance, we propose a dehazing model consisting of a smoothed dilated convolution, a perceptual loss function and a rotational loss function under self-supervised learning. For objective performance evaluation of the proposed techniques, we conducted experiments on the D-HAZY dataset and with real hazy images. The performance of the proposed method was demonstrated through qualitative and quantitative analysis.
Å°¿öµå(Keyword) ¾È°³ Á¦°Å   ¼øȯ Àû´ëÀû »ý¼º ½Å°æ¸Á   ÀÚ±â Áöµµ ÇнÀ   ȸÀü ¼Õ½Ç ÇÔ¼ö   Áö°¢Àû ¼Õ½Ç ÇÔ¼ö   È®Àå ÇÕ¼º°ö ½Å°æ¸Á   dehazing   cyclegan   self-supervised learning   rotation loss   perceptual loss   smoothed dilated convolution  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå