• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.646-647
• /
• 2022

Multiview stereo (MVS) 3D reconstruction of a scene from images is a fundamental computer vision problem that has been thoroughly researched in recent times. Traditionally, MVS approaches create dense correspondences by constructing regularizations and hand-crafted similarity metrics. Although these techniques have achieved excellent results in the best Lambertian conditions, traditional MVS algorithms still contain a lot of artifacts. Therefore, in this study, we suggest using a transformer network to accelerate the MVS reconstruction. The network is based on a transformer model and can extract dense features with 3D consistency and global context, which are necessary to provide accurate matching for MVS.

• 정보처리학회논문지B
• /
• 제11B권2호
• /
• pp.133-140
• /
• 2004

최근 치과 분야의 정보화는 환자자료와 진단영상의 취득과 관리 등을 포함하는 통합 정보화시스템으로써 급속히 발전되었다. 이러한 시스템이 성공하기 위해선 의사가 정확하게 질환을 진단하고 치료하도록 양질의 정보를 제공하며 환자들에게 필요한 고가의 치료를 효과적으로 설득할 수 있는 기능이 확보되어야 한다. 이러한 측면에서 치과분야 시뮬레이션이 가능한 3차원 재구성된 치아모델이 필요하다 치과분야의 치아조작은 대부분 개별 치아 단위로 이루어진다. 따라서 3차원 치아 재구성 시스템은 개변치아의 영역분할과 치아에 맞는 재구성기술이 요구된다. 본 논문에서 적응 최적 임계화를 사용한 치아단위 영역분할 방안과 분할된 경계를 사용한 윤곽선 기반방식의 치아 재구성방안을 제안한다. 즉, 연속된 CT영상에서 개별치아 영역을 정확히 분할하기 위해 슬라이스마다 적응적으로 결정된 최적의 임계치를 사용하여 각 치아를 인접한 이웃 치아와 치조골로부터 분리한다. 분할결과는 3차원 재구성되어 개별 치아를 조작하는 사용자의 입력에 따라 3차원 공간상에서 치아의 이동, 발거 동작을 바탕으로 치과 진료의 시뮬레이션을 가능하게 한다.

• 한국정보통신학회논문지
• /
• 제10권10호
• /
• pp.1848-1853
• /
• 2006

본 논문에서는 3차원 집적 영상 기술에서 렌즈배열 모델을 적용하여 컴퓨터적으로 해상도가 개선된 3차원 영상을 재생하는 방법을 제안하고, 그 성능을 분석한다. 기존의 보고된 컴퓨터 적 시점 재생 방법은 핀홀 배열 모델에 기초하지만, 제안하는 방법은 렌즈 배열 모델을 적용하기 때문에 동일한 요소영상에서 다수의 픽셀을 추출하여 높은 해상도를 얻을 수 있다. 제안한 방법의 유용함을 보이기 위해 기초적인 실험을 수행하고 그 결과를 보고한다.

• 한국멀티미디어학회논문지
• /
• 제12권9호
• /
• pp.1217-1232
• /
• 2009

본 논문에서는 실외에서 촬영된 비교정 영상으로부터 3차원 건물 구조를 복원하는 반자동화 방법론을 제안한다. 사용자는 관심있는 건물을 임의의 위치에서 촬영한다. 본 논문에서 제안하는 시스템은 먼저, 입력영상에 대하여 SIFT 알고리즘을 이용하여 특징점과 대응점을 추출한다. 두 번째로, 각 영상에 존재하는 선과 소실점을 추정하고, 추정된 소실점으로 추출한 선들을 그룹화 한다. 다음으로, 각 영상 간의 관계를 대응점의 개수로 정의한 인접 그래프를 이용하여 입력 영상에 대한 순서를 정의하여, 각 영상을 촬영한 카메라의 위치 정보를 보정한다. 최종적으로 추정한 카메라의 정보와 각 영상에서 그룹화된 선을 이용하여 건물의 대략적인 3차원 구조를 복원한다. 하프 에지(half-edge) 자료 구조와 오일러 연산자(Euler operator)를 이용한 상세 모델링을 수행함으로써 완성된 건물 구조를 복원할 수 있다. 본 논문에서는 자동으로 추출된 기하학적 정보를 이용하여 최소한의 사용자 입력으로 건물을 복원 할 수 있도록 하였다.

• 한국정밀공학회지
• /
• 제10권4호
• /
• pp.81-93
• /
• 1993

The three dimensional(3D) shape reconstruction from two dimensional(2D) cross-sections can be completed through three main phases : the input compilation, the triangular grid formation, and the smooth surface construction. In the input compilation phase, the cross-sections are analyzed to exctract the input data required for the shape reconstruction. This data includes the number of polygonized contours per cross-section and the vertices defining each polygonized contour. In the triangular grid formation phase, a triangular grid, leading to a polyhedral approximations, is constructed by extracting all the information concerning contour links between two adjacent cross- sections and then performing the appropriate triangulation procedure for each contour link. In the smooth surface construction phase, a smooth composite surface interpolating all vertices on the triangular grid is constructed. Both the smooth surface and the polyhedral approximation can be used as reconstructed models of the object. This paper proposes a new method for reconstructing the geometric model of a 3D objdect from a sequence of planar contours representing 2D cross-sections of the objdect. The method includes the triangular grid formation algorithms for contour closing, one-to-one branching, and one-to-many braanching, and many-to-many branching. The shape reconstruction method has been implemented on a SUN workstation in C.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 1999년도 추계학술대회
• /
• pp.565-574
• /
• 1999

In reverse engineering area, it is rapidly developing reconstruction of surfaces from scanning or digitizing data, but geometric models of existing objects unavailable many industries. This paper describes new methodology of reverse engineering area, good strategies and important algorithms in reverse engineering area. Furthermore, proposing reconstruction of surface technique is presented. A method find base geometry and blending surface between them. Each based geometry is divided by triangular patch which are compared their normal vector for face grouping. Each group is categorized analytical surface such as a part of the cylinder, the sphere, the cone, and the plane that mean each based geometry surface. And then, each based geometry surface is implemented infinitive surface. Infinitive average surface's intersections are trimmed boundary representation model reconstruction. This method has several benefits such as the time efficiency and automatic functional modeling system in reverse engineering. Especially, it can be applied 3D scanner and 3D copier.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4463-4482
• /
• 2020

Mesh model generated from 3D reconstruction usually comes with lots of noise, which challenges the performance and robustness of mesh simplification approaches. To overcome this problem, we present a novel method for mesh simplification which could preserve structure and improve the accuracy. Our algorithm considers both the planar structures and linear features. In the preprocessing step, it automatically detects a set of planar structures through an iterative diffusion approach based on Region Seed Growing algorithm; then robust linear features of the mesh model are extracted by exploiting image information and planar structures jointly; finally we simplify the mesh model with plane constraint QEM and linear feature preserving strategies. The proposed method can overcome the known problem that current simplification methods usually degrade the structural characteristics, especially when the decimation is extreme. Our experimental results demonstrate that the proposed method, compared to other simplification algorithms, can effectively improve the quality of mesh and yield an increased robustness on noisy input mesh.

• International journal of advanced smart convergence
• /
• 제5권4호
• /
• pp.1-9
• /
• 2016

In order to reconstruct a 3D model in video sequences, to select key frames that are easy to estimate a geometric model is essential. This paper proposes a method to easily extract informative frames from a handheld video. The method combines selection criteria based on appropriate-baseline determination between frames, frame jumping for fast searching in the video, geometric robust information criterion (GRIC) scores for the frame-to-frame homography and fundamental matrix, and blurry-frame removal. Through experiments with videos taken in indoor space, the proposed method shows creating a more robust 3D point cloud than existing methods, even in the presence of motion blur and degenerate motions.

• Journal of Information Display
• /
• 제4권3호
• /
• pp.29-34
• /
• 2003

At the paper the method of 3D holographic moving image reconstruction is discused. The main idea of this method is based on the substitution of optically created static hologram by equal diffraction array created by acoustical (AO) field which formed by bulk sound waves. Such sound field can be considered as dynamic optical hologram, which is electrically controlled. At the certain moment of time when the whole hologram already formed, the reference optical beam illuminates it, and due to acoustooptical interaction the original optical image is reconstructed. As the acoustically created dynamic optical hologram is electronically controlled, it can be used for moving 3-dimentional scene reconstruction in real time. The architecture of holographic display for moving scene reconstruction is presented at this paper. The calculated variant of such display laboratory model is given and discussed. The mathematical simulation of step by step images recording and reconstruction is given. The pictures of calculated reconstructed images are presented. The prospects, application areas, shortcomings and main problems are discussed.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2010년도 춘계학술대회 논문집
• /
• pp.1407-1408
• /
• 2010