Zobrazeno 1 - 10
of 68
pro vyhledávání: '"Heejune Ahn"'
Publikováno v:
IEEE Access, Vol 10, Pp 75859-75871 (2022)
The shape and pose estimation of a human body are essential for human behavior analysis, sports and medical analysis, and virtual reality. Although 2D image data are much easier to acquire than 3D scan data, the estimation accuracy using 2D images is
Externí odkaz:
https://doaj.org/article/1d5c781c1ff142bb92d83ebfaf019ac6
Publikováno v:
IEEE Access, Vol 9, Pp 30960-30978 (2021)
Image-based virtual try-on (VTON) systems based on deep learning have attracted research and commercial interests. Although they show their strengths in blending the person and try-on clothing image and synthesizing the dis-occluded regions, their re
Externí odkaz:
https://doaj.org/article/e0c6f7f12ed5461fa332452f0fbf52b2
Publikováno v:
IEEE Access, Vol 9, Pp 114367-114380 (2021)
Recently, image-based virtual try-on (VTON) systems using deep generative models have drawn significant research attention. However, the 2D clothing shape transform methods in the earlier works show serious limitations in 3D clothing deformation requ
Externí odkaz:
https://doaj.org/article/944512516f16477594849cbca54c5339
Publikováno v:
Sensors, Vol 20, Iss 1, p 92 (2019)
In this paper, a multi-frame based homography estimation method is proposed for video stitching in static camera environments. A homography that is robust against spatio-temporally induced noise can be estimated by intervals, using feature points ext
Externí odkaz:
https://doaj.org/article/8eff667904ef4b48a9540b761ad41d4a
Publikováno v:
International Journal of Advanced Robotic Systems, Vol 9 (2012)
Recently the component-based approach has become a major trend in intelligent service robot development due to its reusability and productivity. The framework in a component-based system should provide essential services for application components. H
Externí odkaz:
https://doaj.org/article/13a8ea983a5f406b8f81c86f382bc919
Autor:
Thi Thuy Hoang, Heejune Ahn
Publikováno v:
Journal of Information & Communication Convergence Engineering; Dec2023, Vol. 21 Issue 4, p337-345, 9p
Publikováno v:
2022 International Conference on Multimedia Analysis and Pattern Recognition (MAPR).
Publikováno v:
IEEE Access, Vol 9, Pp 114367-114380 (2021)
Recently, image-based virtual try-on (VTON) systems using deep generative models have drawn significant research attention. However, the 2D clothing shape transform methods in the earlier works show serious limitations in 3D clothing deformation requ
Autor:
Heejune Ahn, Matiur Rahman Minar
Publikováno v:
Computer Vision – ACCV 2020 ISBN: 9783030695439
ACCV (6)
ACCV (6)
Virtual clothing try-on, transferring a clothing image onto a target person image, is drawing industrial and research attention. Both 2D image-based and 3D model-based methods proposed recently have their benefits and limitations. Whereas 3D model-ba
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3c7b9fda2e6d8cd04ae9caeff6985c06
https://doi.org/10.1007/978-3-030-69544-6_10
https://doi.org/10.1007/978-3-030-69544-6_10
Publikováno v:
Sensors
Volume 20
Issue 1
Sensors (Basel, Switzerland)
Sensors, Vol 20, Iss 1, p 92 (2019)
Volume 20
Issue 1
Sensors (Basel, Switzerland)
Sensors, Vol 20, Iss 1, p 92 (2019)
In this paper, a multi-frame based homography estimation method is proposed for video stitching in static camera environments. A homography that is robust against spatio-temporally induced noise can be estimated by intervals, using feature points ext