• Journal of the Korea Computer Graphics Society
• /
• v.27 no.3
• /
• pp.31-42
• /
• 2021

We propose a deep learning-based method that can estimate an appropriate lighting of both indoor and outdoor images. The method consists of two networks: Crop-to-PanoLDR network and LDR-to-HDR network. The Crop-to-PanoLDR network predicts a low dynamic range (LDR) environment map from a single partially observed normal field of view image, and the LDR-to-HDR network transforms the predicted LDR image into a high dynamic range (HDR) environment map which includes the high intensity light information. The HDR environment map generated through this process is applied when rendering virtual objects in the given image. The direction of the estimated light along with ambient light illuminating the virtual object is examined to verify the effectiveness of the proposed method. For this, the results from our method are compared with those from the methods that consider either indoor images or outdoor images only. In addition, the effect of the loss function, which plays the role of classifying images into indoor or outdoor was tested and verified. Finally, a user test was conducted to compare the quality of the environment map created in this study with those created by existing research.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04a
• /
• pp.685-687
• /
• 2004

본 논문에서는 우선 단말기에서 이미지 및 폰트를 효율적으로 처리할 수 있는 비트맵 처리 기법을 제안하고 이를 이용한 이미지 및 폰트 처리 시스템을 소개 하고자 한다. 초기에는 컴퓨터 상에 문자를 표현하기 위하여 아스키코드가 개발되었고 이에 표현하지 못하는 부분을 더하고자 유니코드가 개발되어 사용하고 있으나 코드에 대한 표준화 작업은 지금도 계속 되고 있다. 이러한 아스키코드와 유니코드를 무선 단말기상에 적용하고자 하는 시도는 많이 했지만 시간과 노력이 많이 요구되는 비효율적인 잔업이 계속 되어 온 것도 사실이다. 본 논문에서는 이러한 문제점을 채결하고자 아스키코드 및 유니코드를 무선 단말기에 적용시키는 일련의 과정을 단축하고 능률적인 처리시스템을 소개하고자 한다. 본 연구에서는 이미지 및 폰트 처리의 불필요한 작업을 단축하여 최소 비용의 처리 시스템을 설계 및 구현하였다.

• Broadcasting and Media Magazine
• /
• v.18 no.3
• /
• pp.95-108
• /
• 2013

디지털 홀로그래픽 현미경이나 정량적 위상 현미경(quantitative phase microscopy)과 같은 기존의 간섭현미경은 3차원 이미징 기술로 분류되는데, 이는 획득한 이미지의 복소장(complex field)을 계산을 통해 다른 깊이로 전파시킬 수 있기 때문이다. 그러나 엄밀한 의미에서는 하나의 복소장 이미지는 단지 2차원 맵이기 때문에 근본적으로는 샘플의 2차원 정보만을 가지고, 물체의 3차원 구조의 일부분을 측정하는 것에 지나지 않는다. 본 논문에서는 1969년에 Wolf가 제안한[1,2] 홀로그래픽 회절 토모그래피(Optical Diffraction Tomography: ODT)를 실험적으로 구현한 3차원 위상 현미경(Tomographic Phase Microscopy: TPM)을 소개하고자 한다. TPM은 샘플을 다양한 각도로 조명하여 서로 다른 입사각에 대해 복소장 이미지를 얻고, ODT를 통해서 샘플의 3차원 구조를 복원해내는 기술이다. 보다 구체적으로는 다양하고 독립적인 2차원 이미지들을 샘플의 3차원 푸리에 공간에 맵핑함으로써 샘플 단면의 흡수율과 굴절률을 복원할 수 있다. 굴절률은 분자 농도와 비례하기 때문에, 살아있는 세포에 대한 굴절률의 3차원 맵을 얻을 수 있으면 세포 내부의 분자 구성을 연구할 수 있고, 이를 통해 다양한 생의학적 응용을 연구할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.562-565
• /
• 2021

스타일 변환 모델은 이미지 전체나 이미지 내에서 사용자가 지정한 영역을 대상으로 스타일을 변환시킨다. 이런 방식은 이미지 내의 다수의 객체에 대해 스타일 변환을 시행할 때 일일이 영역을 지정해 줘야 한다는 불편함과 결과물의 전체 해상도가 떨어진다는 한계를 가지고 있다. 본 논문에서는 이런 한계들을 극복하기 위해 객체탐지 모델과 스타일변환 모델을 연동한 객체스타일변환모델을 제안하고 모델 간 연동방법에 대해 자세히 서술한다. 객체탐지모델인 Mask R-CNN 을 통해 필요한 객체를 탐지하고 탐지한 객체의 특징맵들을 스타일변환 모델인 zi2zi 의 입력 값으로 전달하여 이미지 내의 필요한 객체들만 스타일변환이 이루어지도록 모델이 동작한다. 이러한 모델은 기존에 있는 두 모델을 재사용함으로써 모델을 처음부터 새로 설계할 필요가 없다는 장점이 있으며, 공개된 다양한 모델들을 서로 융합하여 사용할 수 있는 방법을 제시하는데 도움을 줄 것이다.

• Science of Emotion and Sensibility
• /
• v.16 no.1
• /
• pp.29-42
• /
• 2013

In this paper, we analyze the effect of the depth perception, volume perception and visual discomfort according to the change of the quality of the depth image and the depth of the major object. For the analysis, a 2D image was converted to eighteen 3D images using depth images generated based on the different depth position of a major object and background, which were represented in three detail levels. The subjective test was carried out using eighteen 3D images so that the degrees of the depth perception, volume perception and visual discomfort recognized by the subjects were investigated according to the change in the depth position of the major object and the quality of depth map. The absolute depth position of a major object and the relative depth difference between background and the major object were adjusted in three levels, respectively. The details of the depth map was also represented in three levels. Experimental results showed that the quality of the depth image differently affected the depth perception, volume perception and visual discomfort according to the absolute and relative depth position of the major object. In the case of the cardboard depth image, it severely damaged the volume perception regardless of the depth position of the major object. Especially, the depth perception was also more severely deteriorated by the cardboard depth image as the major object was located inside the screen than outside the screen. Furthermore, the subjects did not felt the difference of the depth perception, volume perception and visual comport from the 3D images generated by the detail depth map and by the rough depth map. As a result, it was analyzed that the excessively detail depth map was not necessary for enhancement of the stereoscopic perception in the 2D-to-3D conversion.

• The KIPS Transactions:PartB
• /
• v.14B no.3 s.113
• /
• pp.171-182
• /
• 2007

We propose a simple method for tracking a nonparameterized subject contour in a single video stream with a moving camera and changing background. Then we present a method to eliminate the tracked contour object by replacing with the background scene we get from other frame. First we track the object using LOD (Level-of-Detail) canny edge maps, then we generate background of each image frame and replace the tracked object in a scene by a background image from other frame that is not occluded by the tracked object. Our tracking method is based on level-of-detail (LOD) modified Canny edge maps and graph-based routing operations on the LOD maps. We get more edge pixels along LOD hierarchy. Our accurate tracking is based on reducing effects from irrelevant edges by selecting the stronger edge pixels, thereby relying on the current frame edge pixel as much as possible. The first frame background scene is determined by camera motion, camera movement between two image frames, and other background scenes are computed from the previous background scenes. The computed background scenes are used to eliminate the tracked object from the scene. In order to remove the tracked object, we generate approximated background for the first frame. Background images for subsequent frames are based on the first frame background or previous frame images. This approach is based on computing camera motion. Our experimental results show that our method works nice for moderate camera movement with small object shape changes.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2007.05a
• /
• pp.164-167
• /
• 2007

2D 평면상에 이미지를 매핑 하는 것은 디자인 프로세스의 초기에 디자인 트랜드를 이해하는 방법의 하나로써 자주 이용되어 왔다. 이러한 유형의 분석 방법은 로봇 디자인 과정에도 필요하다. 본 연구는 로봇 디자인 분석을 위한 보다 진보된 방법으로써의 인터랙티브 맵의 개발과 활용에 초점을 맞추고 있다. 우선 매핑을 위한 기초 자료로써 로봇 디자인 샘플들을 대상으로 휴리스틱 평가와 사용자 설문조사가 실시하였다. 그 결과는 선형 스케일로 변환되었으며 이를 기초로 매크로미디어사의 플래시를 이용한 인터랙티브 매핑 툴이 개발되었다. 본 연구에서 개발된 인터랙티브 맵은 로봇 디자인의 객관적인 특성을 나타내는 6가지 키워드와 사용자의 유형에 따른 9가지 주관적인 선호도로부터 추출되는 2개의 요소들로 구성되는 105가지 맵을 제시할 수 있다. 디자이너가 2가지 다른 요소들을 자유롭게 선택함에 따라 선택된 2가지 요소를 축으로 하는 이미지 맵이 자동적으로 구성되어 제시된다. 본 연구에서는 이와 같은 인터랙티브 맵을 이용해 실제 사례연구를 진행함으로써 디자이너들이 보다 다양한 발견점과 직관적인 통찰력을 얻을 수 있음을 제시하였다. 이러한 방법은 기존의 전통적인 직접적인 2D 매핑과 비교해서 보다 객관적이고 효율적인 방법으로 생각된다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.6
• /
• pp.2807-2814
• /
• 2011

This paper proposes an identification algorithm that detects detrimental digital video contents based on the color space features. In this paper, discrimination algorithm based on a 2-Dimensional Projection Maps is suggested to find targeted video images. First, 2-Dimensional Projection Maps which is extracting the color characteristics of the video images is applied to extract effectively detrimental candidate frames from the videos, and next estimates similarity between the extracted frames and normative images using the suggested algorithm. Then the detrimental candidate frames are selected from the result of similarity evaluation test which uses critical value. In our experimental test, it is suggested that the results of the comparison between the Color Histogram and the 2-Dimensional Projection Maps technique to detect detrimental candidate frames. Through the various experimental data to test the suggested method and the similarity algorithm, detecting method based on the 2-Dimensional Projection Maps show more superior performance than using the Color Histogram technique in calculation speed and identification abilities searching target video images.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.5
• /
• pp.31-40
• /
• 2023

As display resolution increases, many apps also tend to include high-resolution texture maps. Recent advancements in deep-learning-based image super-resolution techniques make it possible to automate high-resolution texture generation. However, there is still a lack of comprehensive analysis of the application of these techniques to texture maps. In this paper, we selected three recent super-resolution techniques, namely BSRGAN, Real-ESRGAN, and SwinIR (classical and real-world image SR), and applied them to upscale texture maps. We then conducted a quantitative and qualitative analysis of the experimental results. The findings revealed various artifacts after upscaling, which indicates that there are still limitations in directly applying super-resolution techniques to texture-map upscaling.

• Journal of the Korean housing association
• /
• v.21 no.1
• /
• pp.67-77
• /
• 2010

Citizen participation in local redevelopment has recently been regarded as essential, since progress in democracy and diversified public interests have contributed to more importance being placed on citizen participation in the implementation of public policies. While the importance of resident participation has been increasingly emphasized in principle, in reality more effort is still required in its application. We need to develop practical strategies of collecting community opinion in order to reflect it in public policy, if we are to achieve a resident and citizen-centered society. The purpose of this study is to develop an image map construction tool that can be applied to the "Maul-Mandulgi" projects as a visualized method to facilitate the exchange of opinions and work toward agreements. The tool is intended to assist public discussion by visualizing policies and plans and reducing the possibility of misunderstanding, so that residents can properly respond to the plans. Second, this study will verify the effectiveness of the tool in the application to local community workshops. The main research method is participant observation method and field study. Major findings are as follows, First, every resident who had participated in previous workshops gathered together, used the tool and represented their opinions unusually more than once. Each resident tried to make sure that other participants appropriately understood his or her opinion. The workshop finished when all participants agreed and produced a consensus. The workshop took much less time, which is in stark contrast to previous workshops in which it took significantly more time to collect opinions. Second, it proved that residents in the redevelopment area can strike a broad agreement by themselves on a method and direction for residential improvement. In previous workshops, conflicts between residents developed over the choice between the two methods, of local improvement and total demolition prior to multi-housing construction. In this study, opinions of residents were not limited to the two methods by finding a winwin solution. Third, the use of the tool kit for image map became efficient for inactive residents to develop their own opinions in regard to the direction and orientations of the residential improvement process. In addition, for those who have either no or a slight understanding of the residential improvement projects, the tool can provide access to information and knowledge. This study concludes that the developed tool for imaging of the redevelopment projection like a design game, rather than using forms of text and speech, can be a useful tool in collecting opinions and forming an agreed opinion for forthcoming residential improvement plans.