• 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¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ÀûÀÀÇü ±íÀÌ ÃßÁ¤±â¸¦ ÀÌ¿ëÇÑ ¹ÌÁö ¹°Ã¼ÀÇ ÀÚ¼¼ ¿¹Ãø
¿µ¹®Á¦¸ñ(English Title) Predicting Unseen Object Pose with an Adaptive Depth Estimator
ÀúÀÚ(Author) ¼Û¼ºÈ£   ±èÀÎö   Sungho Song   Incheol Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 11 NO. 12 PP. 0509 ~ 0516 (2022. 12)
Çѱ۳»¿ë
(Korean Abstract)
3Â÷¿ø °ø°£¿¡¼­ ¹°Ã¼µéÀÇ Á¤È®ÇÑ ÀÚ¼¼ ¿¹ÃøÀº ½Ç³»¿Ü ȯ°æ¿¡¼­ Àå¸é ÀÌÇØ, ·Îº¿ÀÇ ¹°Ã¼ Á¶ÀÛ, ÀÚÀ² ÁÖÇà, Áõ°­ Çö½Ç µî°ú °°Àº ¸¹Àº ÀÀ¿ë ºÐ¾ßµé¿¡¼­ Æø³Ð°Ô È°¿ëµÇ´Â Áß¿äÇÑ ½Ã°¢ ÀÎ½Ä ±â¼úÀÌ´Ù. ¹°Ã¼µéÀÇ ÀÚ¼¼ ¿¹ÃøÀ» À§ÇÑ °ú°Å ¿¬±¸µéÀº ´ëºÎºÐ °¢ ÀÎ½Ä ´ë»ó ¹°Ã¼¸¶´Ù Á¤È®ÇÑ 3Â÷¿ø CAD ¸ðµ¨À» ¿ä±¸ÇÑ´Ù´Â ÇÑ°èÁ¡ÀÌ ÀÖ¾ú´Ù. ÀÌ·¯ÇÑ °ú°Å ¿¬±¸µé°ú´Â ´Þ¸®, º» ³í¹®¿¡¼­´Â 3Â÷¿ø CAD ¸ðµ¨ÀÌ ¾ø¾îµµ RGB Ä÷¯ ¿µ»óµé¸¸ ÀÌ¿ëÇؼ­ ¹ÌÁö ¹°Ã¼µéÀÇ ÀÚ¼¼¸¦ ¿¹ÃøÇس¾ ¼ö ÀÖ´Â »õ·Î¿î ½Å°æ¸Á ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. Á¦¾È ¸ðµ¨Àº ÀûÀÀÇü ±íÀÌ ÃßÁ¤±âÀÎ AdaBins¸¦ ÀÌ¿ëÇÏ¿© ½º½º·Î ¹ÌÁö ¹°Ã¼ ÀÚ¼¼ ¿¹Ãø¿¡ ÇÊ¿äÇÑ °¢ ¹°Ã¼ÀÇ ±íÀÌ Áöµµ¸¦ È¿°úÀûÀ¸·Î ÃßÁ¤Çس¾ ¼ö ÀÖ´Ù. º¥Ä¡¸¶Å© µ¥ÀÌÅÍ ÁýÇÕµéÀ» ÀÌ¿ëÇÑ ´Ù¾çÇÑ ½ÇÇèµéÀ» ÅëÇØ, º» ³í¹®¿¡¼­ Á¦¾ÈÇÑ ¸ðµ¨ÀÇ À¯¿ë¼º°ú ¼º´ÉÀ» Æò°¡ÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Accurate pose prediction of objects in 3D space is an important visual recognition technique widely used in many applications such as scene understanding in both indoor and outdoor environments, robotic object manipulation, autonomous driving, and augmented reality. Most previous works for object pose estimation have the limitation that they require an exact 3D CAD model for each object. Unlike such previous works, this paper proposes a novel neural network model that can predict the poses of unknown objects based on only their RGB color images without the corresponding 3D CAD models. The proposed model can obtain depth maps required for unknown object pose prediction by using an adaptive depth estimator, AdaBins,. In this paper, we evaluate the usefulness and the performance of the proposed model through experiments using benchmark datasets.
Å°¿öµå(Keyword) 3D ºñÀü   ¹ÌÁö ¹°Ã¼   6D ÀÚ¼¼ ¿¹Ãø   ±íÀÌ ÃßÁ¤   ½ÉÃþ ½Å°æ¸Á   3D Vision   Unknown Object   6D Pose Prediction   Depth Estimation   Deep Neural Network  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå