• 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.

• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2489-2491
• /
• 1998

The study of 3D image reconstruction re has developed along the progress of computer. Therfore Great deal of research on it have been done. 3D medical image reconstruction techniques are useful to figure out human's complex 3D structures from the set of 2D section. But 3D medical image reconstruction require a lot of calculation, it takes long time and expensive system. That gives a reason to the improvement of study on speed. In this paper. applying the interpolation to only the part which can appear as cube, I come up with a method that calculates the speed by reducing the a mount of calculation.

• Journal of Korea Multimedia Society
• /
• v.22 no.10
• /
• pp.1142-1148
• /
• 2019

Reconstruction of the three-dimensional (3D) environment is a key aspect of augmented reality and augmented virtuality, which utilize and incorporate a user's surroundings. Such reconstruction can be easily realized by employing a Kinect device. However, multiple Kinect devices are required for enhancing the reconstruction density and for spatial expansion. While employing multiple Kinect devices, they must be calibrated with respect to each other in advance, and a marker is often used for this purpose. However, a marker needs to be placed at each calibration, and the result of marker detection significantly affects the calibration accuracy. Therefore, a user-friendly, efficient, accurate, and marker-less method for calibrating multiple Kinect devices is proposed in this study. The proposed method includes a joint tracking algorithm for approximate calibration, and the obtained result is further refined by applying the iterative closest point algorithm. Experimental results indicate that the proposed method is a convenient alternative to conventional marker-based methods for calibrating multiple Kinect devices. Hence, the proposed method can be incorporated in various applications of augmented reality and augmented virtuality that require 3D environment reconstruction by employing multiple Kinect devices.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.4C
• /
• pp.381-390
• /
• 2006

This paper proposes a new technque of the camera calibration to be computed a homography between the planar patterns taken by a single image to be located at the three planar patterns from uncalibrated images. It is essential to calibrate a camera for 3-dimensional reconstruction from uncalibrated image. Since the proposed method should be computed from the homography among the three planar patterns from a single image, it is implemented to more easily and simply to recover 3D reconstruction of an object than the conventional. Experimental results show the performances of the proposed method are the better than the conventional. We demonstrate examples of recovering 3D reconstruction using the proposed algorithm from uncalibrated images.

• Journal of International Society for Simulation Surgery
• /
• v.2 no.2
• /
• pp.90-93
• /
• 2015

The fibula free flap has now become the most reliable and frequently used option for mandible reconstruction. Recently, three dimensional images and printing technologies are applied to mandibular reconstruction. We introduce our recent experience of mandibular reconstruction using three dimensionally planned fibula free flap in a patient with gunshot injury. The defect was virtually reconstructed with three-dimensional image. Because bone fragments are dislocated from original position, relocation was necessary. Fragments are virtually relocated to original position using mirror image of unaffected right side of the mandible. A medical rapid prototyping (MRP) model and cutting guide was made with 3D printer. Titanium reconstruction plate was adapted to the MRP model manually. 7 cm-sized fibula bone flap was designed on left lower leg. After dissection, proximal and distal margin of fibula flap was osteotomized by using three dimensional cutting guide. Segmentation was also done as planned. The fibula bone flap was attached to the inner side of the prebent reconstruction plate and fixed with screws. Postoperative evaluation was done by comparison between preoperative planning and surgical outcome. Although dislocated condyle is still not in ideal position, we can see that reconstruction was done as planned.

• Proceedings of the IEEK Conference
• /
• 2004.08c
• /
• pp.804-809
• /
• 2004

It is essential to calibrate a camera in order to recover 3-dimensional reconstruction from uncalibrated images. This paper proposes a new technique of the camera calibration using a homography between the planar patterns image taken by the camera, which is located at the three planar patterns image. Since the proposed method should be computed from the homography among the three planar patterns from a single image, it is implemented more easily and simply to recover 3D object than the conventional. Experimental results show the performances of the proposed method are the better than the conventional. We demonstrate the examples of 3D reconstruction using the proposed algorithm from image sequence.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.470-473
• /
• 2005

This paper proposes a reconstruction method for the shape and color information of 3-dimensional buildings. The proposed method is range scanning by laser range finder and image coordinates' color information mapping to laser coordinate by a fixed CCD camera on laser range finder. And we make a 'Far-View' using high-resolution satellite image. The 'Far-View' is created that the height of building using DEM after contours of building extraction. The user select a region of 'Far View' and then, appear detailed 3D-reconstruction of building The outcomes apply to city plan, 3D-environment game and movie background etc.

• ETRI Journal
• /
• v.42 no.3
• /
• pp.420-432
• /
• 2020

The reconstruction of archaeological fragments in 3D geometry is an important problem in pattern recognition and computer vision. Therefore, we implement an algorithm with the help of a 3D model to perform reconstruction from the real datasets using the slope features. This approach avoids the problem of gaps created through the loss of parts of the artifacts. Therefore, the aim of this study is to assemble the object without previous knowledge about the form of the original object. We utilize the edges of the fragments as an important feature in reconstructing the objects and apply multiple procedures to extract the 3D edge points. In order to assign the positions of the unknown parts that are supposed to match, the contour must be divided into four parts. Furthermore, to classify the fragments under reconstruction, we apply a backpropagation neural network. We test the algorithm on several models of ceramic fragments. It achieves highly accurate results in reconstructing the objects into their original forms, in spite of absent pieces.

• ETRI Journal
• /
• v.28 no.4
• /
• pp.521-524
• /
• 2006

In this letter, we propose a novel computational integral imaging reconstruction technique based on a lenslet array model. The proposed technique provides improvement of viewing images by extracting multiple pixels from elemental images according to ray tracing based on the lenslet array model. To show the feasibility of the proposed technique, we analyze it according to ray optics and present the experimental results.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.71-74
• /
• 2009

The data-flow paradigm has been employed in various application areas. It is particularly useful where large data-streams must be processed, for example in video and audio processing, or for scientific visualization. A video-based 3D reconstruction system should process multiple synchronized video streams. The system exhibits many properties that can be targeted using a data-flow approach that is naturally divided into a sequence of processing tasks. In this paper we introduce our concept to apply the data-flow approach to a multi-video 3D reconstruction system.