• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.106-108
• /
• 2022

이미지 기반 3D 형상 복원에 있어서, 이미지에 보이지 않는 폐색(Occlusion) 영역 부분에 대한 정보가 손실되므로 완전한 복원에 어려움이 있으며, 세밀한 텍스쳐(Texture) 표현이 이루어지지 않고 심한 평활화(Smoothing)나 고립된 노이즈 메쉬(Isolated Noise Mesh) 등 구조적 훼손이 발생한다. 주로 깊은 신경망을 이용하여, 음함수(Implicit Function) 기반 방법은 사전훈련이 완료된 보조 신경망들을 전면부에 배치하거나, Hourglass 등 임베딩(Embedding) 아키텍처를 추가하거나, 또는 표면 법선(Surface Normal)과 같은 환시(Hallucination)를 생성하여 신경망에 입력하기도 한다. 이 논문에서는, 인물의 이미지를 입력받아 색상, 머리카락 및 의상을 포함하는 완전 3D 인간 복원 기술들을 조망해본다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.103-110
• /
• 2011

A widely used 3D face reconstruction method, structure from motion(SfM), shows robust performance when frontal, left, and right face images are used. However, this method cannot reconstruct a self-occluded facial part correctly when only one side view face images are used because only partial facial feature points can be used in this case. In order to solve the problem, the proposed method exploit a constrain that is bilateral symmetry of human faces in order to generate bilateral facial feature points and use both input facial feature points and generated facial feature points to reconstruct a 3D face. For quantitative evaluation of the proposed method, 3D faces were obtained from a 3D face scanner and compared with the reconstructed 3D faces. The experimental results show that the proposed 3D face reconstruction method based on both facial feature points outperforms the previous 3D face reconstruction method based on only partial facial feature points.

• Conservation Science in Museum
• /
• v.26
• /
• pp.25-34
• /
• 2021

3D printing technology has been actively applied for the restoration of cultural properties. However, its application to the restoration of glass cultural properties has not yet been reported and thus requires further study. In this study, 3D printing technology was used to restore a defective part of a glass sarira bottle that forms an element of a series of sarira reliquaries commissioned by Yi Seonggye (known as King Taejo after founding the Joseon Dynasty) that was excavated from Geumgangsan Mountain (designated as Treasure No. 1925) and is currently housed at the National Museum of Korea. The defective area was reproduced using 3D printing and the printed reproduction was reproduced again using an epoxy resin. This latter piece was used as the restoration component rather than the 3D printed element. After the completion of the conservation treatment, the materials used for the 3D printing were compared with transparent materials used to restore ceramics to evaluate their usability and stability. A total of five specimens were produced, including from photocurable resin made by a stereo lithography apparatus (SLA), epoxy resin, acrylic resin, and more. They were exposed to UV for 96 hours to test for yellowing. Of the two specimens made of photocurable resins and exposed to UV, one was sprayed with a UV blocking agent but the other was exposed as-is. The UV exposure test showed that the specimen made by the SLA and sprayed with a UV blocking agent and the specimen made of epoxy resin were stable in terms of yellowing with a change in the b-value was less than 1. They are thus considered to be suitable materials for the restoration of glass cultural properties. Such glass cultural properties are often diverse in shape and their restoration can be difficult as they generally consist of a range of complex parts that hamper restoration. In this regard, diverse materials should be considered when selecting materials for the restoration of glass cultural properties.

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.4
• /
• pp.168-176
• /
• 2005

We propose a method for 3-dimensionally reconstructing an object using a line that includes the midpoint information from a single image. A pre-defined polygon is used as the primitive and the recovery is processed from a single image. The 3D reconstruction is processed by mapping the correspondence point of the primitive model onto the photo. In the recent work, the reconstructions of camera parameters or error minimizing methods through iterations were used for model-based 3D reconstruction. However, we proposed a method for the 3D reconstruction of primitive that consists of the segments and the center points of the segments for the reconstruction process. This method enables the reconstruction of the primitive model to be processed using only the focal length of various camera parameters during the segment reconstruction process.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2003.10a
• /
• pp.193-197
• /
• 2003

우수한 문화유산을 보유하고 있는 우리나라는 그간 전쟁과 관리소홀로 인하여 많이 파괴되고 유실되는 피해를 입어왔다. 한번 손실된 문화재는 기존 자료 없이는 완전복구가 어려운 실정이며, 이러한 문화재의 복원을 위해 그 모습을 수치화시켜 영구 보전함으로써 그 활용가치를 높일 수 있다. 또한, 문화재의 복원 전·후의 모습을 체계적으로 정리하기 위해서 문화재의 3차원 구현을 통한 자료의 전산화 작업이 필요하다. 따라서, 본 연구에서는 수치사진측량용 카메라를 이용하여 봉분을 촬영하고, 이렇게 취득 데이터를 사용하여 3차원형상을 수치화 하여 복원 이전의 발굴상태를 영구히 보존함과 동시에 발굴된 유적을 기초로 하여 복원시킨 봉분의 형상을 추측하기는 자료로도 활용할 수 있다. 이러한 복원 작업을 효율적이고, 신속하게 분석하여 재현함으로써 문화재의 유지관리·복원을 위한 기초 자료기반을 구축함에 그 목적이 있다.

• Journal of the HCI Society of Korea
• /
• v.2 no.2
• /
• pp.1-9
• /
• 2007

In this paper, we propose a reconstruction technique of the lost hair region for 3D human actor modeling. An active depth sensor system can simultaneously capture both color and geometry information of any objects in real-time. However, it cannot acquire some regions whose surfaces are shiny and dark. Therefore, to get a natural 3D human model, the lost region in depth image should be recovered, especially human hair region. The recovery is performed using both color and depth images. We find out the hair region using color image first. After the boundary of hair region is estimated, the inside of hair region is estimated using an interpolation technique and closing operation. A 3D mesh model is generated after performing a series of operations including adaptive sampling, triangulation, mesh smoothing, and texture mapping. The proposed method can generate recovered 3D mesh stream automatically. The final 3D human model allows the user view interaction or haptic interaction in realistic broadcasting system.

• Journal of the HCI Society of Korea
• /
• v.1 no.1
• /
• pp.53-61
• /
• 2006

In this paper, we propose a novel method for 3D reconstruction of an indoor scene using a multi-view camera. Until now, numerous disparity estimation algorithms have been developed with their own pros and cons. Thus, we may be given various sorts of depth images. In this paper, we deal with the generation of a 3D surface using several 3D point clouds acquired from a generic multi-view camera. Firstly, a 3D point cloud is estimated based on spatio-temporal property of several 3D point clouds. Secondly, the evaluated 3D point clouds, acquired from two viewpoints, are projected onto the same image plane to find correspondences, and registration is conducted through minimizing errors. Finally, a surface is created by fine-tuning 3D coordinates of point clouds, acquired from several viewpoints. The proposed method reduces the computational complexity by searching for corresponding points in 2D image plane, and is carried out effectively even if the precision of 3D point cloud is relatively low by exploiting the correlation with the neighborhood. Furthermore, it is possible to reconstruct an indoor environment by depth and color images on several position by using the multi-view camera. The reconstructed model can be adopted for interaction with as well as navigation in a virtual environment, and Mediated Reality (MR) applications.

• The KIPS Transactions:PartB
• /
• v.17B no.3
• /
• pp.215-226
• /
• 2010

The structured-light 3D reconstruction technique uses a coded-pattern to find correspondences between the camera image and the projector image. To calculate the 3D coordinates of the correspondences, it is necessary to calibrate the camera and the projector. In addition, the calibration results affect the accuracy of the 3D reconstruction. Conventional camera-projector calibration techniques commonly require either expensive hardware rigs or complex algorithm. In this paper, we propose an easy camera-projector calibration technique. The proposed technique does not need any hardware rig or complex algorithm. Thus it will enhance the efficiency of structured-light 3D reconstruction. We present two camera-projector systems to show the calibration results. Error analysis on the two systems are done based on the projection error of the camera and the projector, and 3D reconstruction of world reference points.

• Journal of Internet Computing and Services
• /
• v.10 no.4
• /
• pp.25-33
• /
• 2009

In the paper, we proposed a new system to retrieve 3D wrinkle data based on stereo images. Usually, 3D reconstruction based on stereo images or video is very popular and it is the research focus, which has been applied for culture heritage, building and other scene. The target is object measurement, the scene depth calculation and 3D data obtained. There are several challenges in our research. First, it is hard to take the full information wrinkle images by cameras because of light influence, skin with non-rigid object and camera performance. We design a particular computer vision system to take winkle images with a long length camera lens. Second, it is difficult to get the dense stereo data because of the hard skin texture image segmentation and corner detection. We focus on semi-dense stereo matching algorithm for the wrinkle depth. Compared with the 3D scanner, our system is much cheaper and compared with the physical modeling based method, our system is more flexible with high performance.

• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.70-78
• /
• 2021

Estimating 3D information from a single image is one of the essential problems in numerous applications. Since a 2D image inherently might originate from an infinite number of different 3D scenes, thus 3D reconstruction from a single image is notoriously challenging. This challenge has been overcame by the advent of recent deep convolutional neural networks (CNNs), by modeling the mapping function between 2D image and 3D information. However, to train such deep CNNs, a massive training data is demanded, but such data is difficult to achieve or even impossible to build. Recent trends thus aim to present deep learning techniques that can be trained in a weakly-supervised manner, with a meta-data without relying on the ground-truth depth data. In this article, we introduce recent developments of weakly-supervised deep learning technique, especially categorized as scene 3D reconstruction and object 3D reconstruction, and discuss limitations and further directions.