Zobrazeno 1 - 10
of 88
pro vyhledávání: '"Won-Sik Cheong"'
Autor:
Eun-bin An, Ayoung Kim, Soon-heung Jung, Sangwoon Kwak, Jin Young Lee, Won-Sik Cheong, Hyon-Gon Choo, Kwang-deok Seo
Publikováno v:
EURASIP Journal on Image and Video Processing, Vol 2024, Iss 1, Pp 1-17 (2024)
Abstract As the performance of machine vision continues to improve, it is being used in various industrial fields to analyze and generate massive amounts of video data. Although the demand for and consumption of video data by machines has increased s
Externí odkaz:
https://doaj.org/article/4b6b565f4af54d799e851b4084647285
Publikováno v:
IEEE Access, Vol 12, Pp 160254-160266 (2024)
Although there are many advantages (e.g., occlusion-robust properties) to be gained by using multi-view inputs for human mesh reconstruction, relatively few studies have been conducted due to the complexity of the fusion process. In this paper, we de
Externí odkaz:
https://doaj.org/article/b600cd7bb6cd4d70bae71d1b1561818b
Autor:
Sangwoon Kwak, Joungil Yun, Jun-Young Jeong, Youngwook Kim, Insung Ihm, Won-Sik Cheong, Jeongil Seo
Publikováno v:
ETRI Journal, Vol 44, Iss 1, Pp 24-37 (2022)
Virtual view synthesis, which generates novel views similar to the characteristics of actually acquired images, is an essential technical component for delivering an immersive video with realistic binocular disparity and smooth motion parallax. This
Externí odkaz:
https://doaj.org/article/43e013228ef54c829a65d608a6389586
Publikováno v:
Sensors, Vol 21, Iss 19, p 6680 (2021)
In this paper, we propose a multi-view stereo matching method, EnSoft3D (Enhanced Soft 3D Reconstruction) to obtain dense and high-quality depth images. Multi-view stereo is one of the high-interest research areas and has wide applications. Motivated
Externí odkaz:
https://doaj.org/article/ba56920a988f4b518d08f3e4a301718a
Autor:
Jungil Yun, Sang-hyo Park, Byung-Gyu Kim, Kug-Jin Yun, Won-Sik Cheong, Dongsan Jun, Taesik Lee
Publikováno v:
Computers, Materials & Continua. 70:2013-2029
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ec6099f791dce8c80bd8aa9e8f89c46d
https://doi.org/10.32604/cmc.2022.019604
https://doi.org/10.32604/cmc.2022.019604
Publikováno v:
International Workshop on Advanced Imaging Technology (IWAIT) 2022.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::82a4375827837e7cf5a71f1202bbc82b
https://doi.org/10.1117/12.2626039
https://doi.org/10.1117/12.2626039
Publikováno v:
2021 36th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC).
The recent success on convolutional neural networks (CNNs) research has triggered the interest to improve the stereo reconstruction. There have been many considerations to reconstruct unstructured general images. However, photos taken in an unstructu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1ee1e177c823604fa5627ff09e739032
https://doi.org/10.1109/itc-cscc52171.2021.9501460
https://doi.org/10.1109/itc-cscc52171.2021.9501460
Publikováno v:
ISCAS
This paper presents a novel structured camera pose estimation framework for mosaic-based omnidirectional imaging, i.e., producing a wide field of view (FoV) image that covers an entire sphere of the surroundings from a set of regular FoV images. With
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6c871242eddd03228aee32df34e89d6c
https://doi.org/10.1109/iscas51556.2021.9401585
https://doi.org/10.1109/iscas51556.2021.9401585
Publikováno v:
VR Workshops
Depth-image-based rendering (DIBR) is a key method for synthesizing virtual views from multiple RGB-D video streams. A challenging issue inherent in this approach is the disocclusion that occurs as the virtual viewpoint moves away from a reference vi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dd196dc8ed16a159e0e7922f76496811
https://doi.org/10.1109/vrw52623.2021.00184
https://doi.org/10.1109/vrw52623.2021.00184
Publikováno v:
ICTC
In the MPEG-VCM framework, an efficient video coding technique while maintaining task performance such as object segmentation is required. In this paper, we introduce the MPEG- VCM framework and show some results of VCM anchor generation on Cityscape
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7a100f32a8e002ae2b4f6c1bcec42568
https://doi.org/10.1109/ictc49870.2020.9289457
https://doi.org/10.1109/ictc49870.2020.9289457