• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.5
• /
• pp.1-11
• /
• 2020

Image-based virtual try-on (VTON) is becoming popular for online apparel shopping, mainly because of not requiring 3D information for try-on clothes and target humans. However, existing 2D algorithms, even when utilizing advanced non-rigid deformation algorithms, cannot handle large spatial transformations for complex target human poses. In this study, we propose a 3D clothing reconstruction method using a 3D human body model. The resulting 3D models of try-on clothes can be more easily deformed when applied to rest posed standard human models. Then, the poses and shapes of 3D clothing models can be transferred to the target human models estimated from 2D images. Finally, the deformed clothing models can be rendered and blended with target human representations. Experimental results with the VITON dataset used in the previous works show that the shapes of reconstructed clothing are significantly more natural, compared to the 2D image-based deformation results when human poses and shapes are estimated accurately.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.3D
• /
• pp.535-540
• /
• 2006

This paper presented an effective strategy to extract the buildings and to reconstruct 3-D buildings using high-resolution multispectral stereo satellite images. Proposed scheme contained three major steps: building enhancement and segmentation using both BDT (Background Discriminant Transformation) and ISODATA algorithm, conjugate building identification using the object matching with Hausdorff distance and color indexing, and 3-D building reconstruction using photogrammetric techniques. IKONOS multispectral stereo images were used to evaluate the scheme. As a result, the BDT technique was verified as an effective tool for enhancing building areas since BDT suppressed the dominance of background to enhance the building as a non-background. In building recognition, color information itself was not enough to identify the conjugate building pairs since most buildings are composed of similar materials such as concrete. When both Hausdorff distance for edge information and color indexing for color information were combined, most segmented buildings in the stereo images were correctly identified. Finally, 3-D building models were successfully generated using the space intersection by the forward RFM (Rational Function Model).

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.3 s.303
• /
• pp.39-52
• /
• 2005

In this paper, a registration method is presented to register partial 3D point clouds, acquired from a multi-view camera, for 3D reconstruction of an indoor environment. In general, conventional registration methods require a high computational complexity and much time for registration. Moreover, these methods are not robust for 3D point cloud which has comparatively low precision. To overcome these drawbacks, a projection-based registration method is proposed. First, depth images are refined based on temporal property by excluding 3D points with a large variation, and spatial property by filling up holes referring neighboring 3D points. Second, 3D point clouds acquired from two views are projected onto the same image plane, and two-step integer mapping is applied to enable modified KLT (Kanade-Lucas-Tomasi) to find correspondences. Then, fine registration is carried out through minimizing distance errors based on adaptive search range. Finally, we calculate a final color referring colors of corresponding points and reconstruct an indoor environment by applying the above procedure to consecutive scenes. The proposed method not only reduces computational complexity by searching for correspondences on a 2D image plane, but also enables effective registration even for 3D points which have low precision. Furthermore, only a few color and depth images are needed to reconstruct an indoor environment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.5
• /
• pp.1171-1176
• /
• 2011

This paper describes an analysis on the relationship between elemental image size and object locations in the computational integral imaging reconstruction and in the pickup using a periodically-distributed lenslet array. A sparse sampling effect arises from a periodically-distributed lenslet array in the pickup of 3D objects. The relationship between elemental image size and object location is also reported. Based on the analysis, a method to eliminate the sparse sampling is proposed. To show the effectiveness of the proposed method, experimental results are carried out. It turns out that the theory works.

• The Journal of the Acoustical Society of Korea
• /
• v.32 no.3
• /
• pp.269-278
• /
• 2013

The speech recording of the National Archives of Korea contains very important traces which represent modern times of Korea. But the way to be recorded by analogue is easily contaminated as time goes by. So it has to be digitalized for management and services. Consequently, restoration method of distorted speech is needed. We propose the four classes for each distortion kind and apply restoration algorithms for the cases of speech level, stationary noise and abrupt noise. As a result, speech volume adjusts to -26 dBov for only on the speech region and SNR improves above 10dB. Especially, conventional way to remove the noise is almost impossible because we need to listen to all of them but it can be more effective by adaptation of auto restoration algorithm.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.521-524
• /
• 2023

본 연구에서는 AI 인공지능을 활용한 통일신라 석탑 '경주 불국사 삼층석탑' 복원을 위해 석탑 3D모델링 과정에 대한 연구를 수행하였다. 산성비로 부식되어 갈라진 더 이상 원본의 형태를 알아 볼 수 없는 현재 통일신라 석탑 형태를 3D모델링 작업을 통하여 AI로 하여금 원활한 교육이 실시 되도록 하는 것을 목표로한다. 본래 제작 되어있는 3D 모델링은 많은 버텍스와 페이스로 학습 데이터가 많아 실제 활용하기에 어려움을 가지고 있다. 때문에 적은 양의 버텍스와 페이스로 새로운 3D 모델링 제작에 대한 필요성에 대해 확인하였다. 본 연구는 그에 필요한 석탑 모델링 과정에 대해 서술한다. 이를 위해 본 논문은 석탑에 대한 구조를 살피고 모델링에 활용된 프로그램의 장단점과 분석을 도출하였다. 본 연구를 통해 석탑 복원에 필요한 3D모델링 프로그램 활용의 전망과 더불어 인공지능 AI의 한계점을 3D 모델링의 정확도와 세밀함을 통하여 타파하고자 하였다.

• The Journal of the Petrological Society of Korea
• /
• v.23 no.2
• /
• pp.139-144
• /
• 2014

A series of the planar cathodoluminescence (CL) and backscattered-electron (BSE) images of magmatic zircon from the Paleozoic Yeongdeok pluton in the southeastern Korean Peninsula were taken using a scanning electron microscope for a 3D reconstruction of internal zonation of zircon. Seven zircon crystals mounted in epoxy were serially polished with average $3{\mu}m$ thickness to their disappearance. Their 3D reconstruction of zonation was performed using the Volume Viewer function in the ImageJ software. The 3D oscillatory zoning pattern of zircon was apparently shown in all the analyzed crystals. This method can further be applied to zircon crystals of multiple growth histories as well as other geological materials.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.3
• /
• pp.1367-1372
• /
• 2011

This paper designed 3D animation in consideration of human characteristics to stimulate their interest and to be more understandable to them. It was also confirmed that, using the 3D animation contents, general people came to recognize the problem of environment pollution and developed desirable attitude and behavior for protecting the environment. Furthermore, this paper suggested the ruins original form restoration technique of the residential environment and the natural environment of Hanyang in the Joseon Dynasty period using the 3D virtual reality digital recovery techniques.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.293-293
• /
• 2017

하천복원 또는 서식환경조성에 있어서 흐름영역을 통한 하천생태계 서식처 공간의 조성은 매우 중요하며 최적서식공간을 조성하기 위한 공간 확보 및 복원의 기술은 가장 중요하게 개발해야할 대상이다. 본 연구에서는 공간 확대에 따른 수환경 변화가 어류 물리서식처에 미치는 영향을 분석하기 위해 2차원 물리서식처 모형인 River2D를 적용하였다. River2D의 구동에 필요한 지형데이터는 만경강 유역의 봉동, 소양, 하리 3개의 지점을 경계지점으로 하여 대상영역 내 저지대 상습 침수구역인 만경강 본류와 소양천 합류지점을 복원대상지로 선정 후, 이 구역의 현재하도(공간복원전)와 합류부에서 제방을 없애 공간을 확보한(공간 복원후) 하도의 지형을 구축하였다. 그리고 과거 만경강 봉동일대에서 출현하였던 감돌고기를 대상어종으로 하여 감돌고기에 대한 생애주기별 서식처 적합도 지수(HSC)를 산정한 결과를 분석에 이용하였고, 유황조건은 IHA를 이용하여 산정된 5가지 유황조건을 경계조건으로 하여 분석을 실시하였다. 가중가용면적-유량관계곡선의 도출을 통해서 최적유량 산정시 중요한 지표인 WUA의 산정결과 현재 하천공간보다 공간 복원후 하천공간이 더 많은 가중가용면적을 확보하고 있음을 알 수 있고 동일한 유황의 조건에서 하천공간의 확보 및 복원을 통해 최소유량의 최대서식처 개선효과를 확인할 수 있었다. 또한 공간복원 후에 감돌고기에 대한 최대 가중가용면적은 20.4% 증가하였고, 최적유량변동은 20m3(57.1%) 저감하는 것을 확인할 수 있었다. 감돌고기의 생애주기별 복합서식처 적합도 분포결과는 복원후 전체 공간분포 중 소양천 합류부 및 복원 홍수터에서 서식처 적합도의 공간분포가 높게 나타났고 가중가용면적도 복원후 산란기(4~6월)에 57.7%, 성장기(7~8월)에 6.0%, 성어기(9~11월)에 41.9%로 가중가용 면적이 증가하였으며, 특히 산란기와 성어기의 가중가용면적이 하천공간 확보를 통해 크게 증가되었다. 이러한 결과들을 바탕으로 수생태계에서 하천어류의 서식환경을 보호하고 유지하기 위해서 적절한 서식공간의 확보가 선행되어야 하며 복원사업에 따른 제방제거 및 하상변동으로 발생하는 유속의 변화로 인한 다양한 영향을 충분히 검토하여야 할 것으로 판단된다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.11b
• /
• pp.487-490
• /
• 2002

이미지를 기반으로 3차원 모델을 생성하기 위한 방법은 많은 사람들의 연구의 대상이 되어 왔다. 본 연구에서는 연속적으로 획득된 여러 장의 이미지로부터 특징점을 추출한 후, 사영복원과 유클리디언 복원을 이용하여 특징점에 대응되는 3차원 데이터를 계산하는 방법을 구현하였고, 이렇게 얻은 3차원 데이터에 텍스쳐 매핑을 결합하여, 보다 사실적인 3차원 모델을 생성할 수 있는 시스템을 구현하였다.