• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권11호
• /
• pp.5506-5521
• /
• 2017

Three-dimensional video (3DV), as the new generation of video format standard, can provide the viewers with a vivid screen sense and a realistic stereo impression. Meanwhile the view synthesis has become an important issue for 3DV application. Differently from the conventional methods based on depth, in this paper we propose a new view synthesis algorithm, which can employ the correlation among views and warp in the image domain only. There are mainly two contributions. One is the incorporation of sobel edge points into feature extraction and matching, which can obtain a better stable homography and then a visual comfortable synthesis view compared to SIFT points only. The other is a novel image blending method proposed to obtain a better synthesis image. Experimental results demonstrate that the proposed method can improve the synthesis quality both in subjectivity and objectivity.

• ETRI Journal
• /
• 제44권1호
• /
• pp.51-61
• /
• 2022

In this paper, we introduced a novel voxel-wise UV parameterization and view-dependent texture synthesis for the immersive rendering of a truncated signed distance field (TSDF) scene model. The proposed UV parameterization delegates a precomputed UV map to each voxel using the UV map lookup table and consequently, enabling efficient and high-quality texture mapping without a complex process. By leveraging the convenient UV parameterization, our view-dependent texture synthesis method extracts a set of local texture maps for each voxel from the multiview color images and separates them into a single view-independent diffuse map and a set of weight coefficients for an orthogonal specular map basis. Furthermore, the view-dependent specular maps for an arbitrary view are estimated by combining the specular weights of each source view using the location of the arbitrary and source viewpoints to generate the view-dependent textures for arbitrary views. The experimental results demonstrate that the proposed method effectively synthesizes texture for an arbitrary view, thereby enabling the visualization of view-dependent effects, such as specularity and mirror reflection.

• ETRI Journal
• /
• 제44권1호
• /
• pp.24-37
• /
• 2022

Virtual view synthesis, which generates novel views similar to the characteristics of actually acquired images, is an essential technical component for delivering an immersive video with realistic binocular disparity and smooth motion parallax. This is typically achieved in sequence by warping the given images to the designated viewing position, blending warped images, and filling the remaining holes. When considering 6DoF use cases with huge motion, the warping method in patch unit is more preferable than other conventional methods running in pixel unit. Regarding the prior case, the quality of synthesized image is highly relevant to the means of blending. Based on such aspect, we proposed a novel blending architecture that exploits the similarity of the directions of rays and the distribution of depth values. By further employing the proposed method, results showed that more enhanced view was synthesized compared with the well-designed synthesizers used within moving picture expert group (MPEG-I). Moreover, we explained the GPU-based implementation synthesizing and rendering views in the level of real time by considering the applicability for immersive video service.

• 방송공학회논문지
• /
• 제11권4호
• /
• pp.507-520
• /
• 2006

본 논문은 다중 카메라에서 얻은 영상과 그 영상으로부터 얻은 깊이영상(depth map)을 사용하여 중간시점에서의 영상을 생성하기 위하여 OpenGL 함수를 적용하는 방법을 소개한다. 기본적으로 영상기반 렌더링 방법은 카메라로 직접 얻은 영상을 그래픽 엔진에 적용하여 결과 영상을 생성하는 것을 의미하지만 주어진 영상 및 깊이정보를 어떻게 그래픽 엔진에 적용시키고 영상을 렌더링 하는지에 관한 방법은 잘 알려져 있지 않다. 본 논문에서는 카메라 정보로 물체가 생성될 공간을 구축하고, 구축된 공간 안에 색상영상과 깊이영상 데이터로 3차원 물체를 형성하여 이를 기반으로 실시간으로 중간영상 결과를 생성하는 방법을 제안하고자 한다. 또한, 중간영상에서의 깊이영상도 추출하는 방법을 소개하도록 하겠다.

• 약학회지
• /
• 제45권1호
• /
• pp.16-22
• /
• 2001

Novel yakuchinone derivatives have been designed, synthesized and evaluated their inhibitory activity of NO production in lipopolysaccharide (LPS)-activated macrophages. From this study, some enone compounds have been found to be highly active in the assay. In view of the importance of NO in septic shock and inflammation, these compounds may be useful candidates for the development of new drug to treat endotoxemia and inflammation accompanying overproduction of NO.

• Toxicological Research
• /
• 제34권4호
• /
• pp.297-302
• /
• 2018

Cells are constantly exposed to endogenous and exogenous chemical and physical agents that damage their genome by forming DNA lesions. These lesions interfere with the normal functions of DNA such as transcription and replication, and need to be either repaired or tolerated. DNA lesions are accurately removed via various repair pathways. In contrast, tolerance mechanisms do not remove lesions but only allow replication to proceed despite the presence of unrepaired lesions. Cells possess two major tolerance strategies, namely translesion synthesis (TLS), which is an error-prone strategy and an accurate strategy based on homologous recombination (homology-dependent gap repair [HDGR]). Thus, the mutation frequency reflects the relative extent to which the two tolerance pathways operate in vivo. In the present paper, we review the present understanding of the mechanisms of TLS and HDGR and propose a novel and comprehensive view of the way both strategies interact and are regulated in vivo.

• 대한임베디드공학회논문지
• /
• 제19권1호
• /
• pp.9-17
• /
• 2024

It is widely recognized that for 3D human pose estimation (HPE), dataset acquisition is expensive and the effectiveness of augmentation techniques of conventional visual recognition tasks is limited. We address these difficulties by presenting a simple but effective method that augments input images in terms of viewpoints when training a 3D human pose estimation (HPE) model. Our intuition is that meaningful variants of the input images for HPE could be obtained by viewing a human instance in the images from an arbitrary viewpoint different from that in the original images. The core idea is to synthesize new images that have self-occlusion and thus are difficult to predict at different viewpoints even with the same pose of the original example. We incorporate this idea into the training procedure of the 3D HPE model as an augmentation stage of the input samples. We show that a strategy for augmenting the synthesized example should be carefully designed in terms of the frequency of performing the augmentation and the selection of viewpoints for synthesizing the samples. To this end, we propose a new metric to measure the prediction difficulty of input images for 3D HPE in terms of the distance between corresponding keypoints on both sides of a human body. Extensive exploration of the space of augmentation probability choices and example selection according to the proposed distance metric leads to a performance gain of up to 6.2% on Human3.6M, the well-known pose estimation dataset.

• 한국컴퓨터정보학회논문지
• /
• 제29권8호
• /
• pp.23-32
• /
• 2024

NVS는 여러 각도와 위치에서 수집한 이미지를 이용해 3차원 공간을 재현하는 연구 분야로, 증강현실, 가상현실, 자율주행, 로봇 네비게이션 등에서 중요성이 커지고 있다. 최근 주목받는 3D-GS 방법론은 기존 NeRF 보다 고품질 장면 생성, 빠른 학습 시간, 실시간 렌더링이 가능하지만, Gaussian points의 밀도 조정 과정에서 전체 Gaussian points 수의 증가로 메모리 소모량 상승과 렌더링 속도가 저하되는 문제가 있다. 이를 개선하기 위해 본 논문에서는 불필요한 Gaussian points를 제거하여 메모리 효율성을 높이는 Gaussian blending 기법과 Gaussian points 감소로 인한 표현력 손실을 최소화하는 깊이 정보 반영 손실 함수를 제안하여 모델의 성능을 보완한다. 실험 결과, Tanks & Temples 벤치마크 데이터셋에서 성능을 유지하면서 Gaussian points 수를 최대 4% 감소시키는 효과를 확인하였다. 따라서 본 논문에서 제안한 방법론은 3D-GS 모델의 경량화 가능성을 실험적으로 증명하였다.

• 한국콘텐츠학회논문지
• /
• 제13권10호
• /
• pp.62-70
• /
• 2013

DIBR(Depth Image Based Rendering)은 참조 영상 및 그와 관련된 깊이지도로부터 자유 시점의 영상을 생성하는 영상 합성 알고리즘이다. DIBR을 통한 영상 합성의 주요 난제 중 하나는 참조영상에서 가려져 있던 영역이 합성 시점에서 드러나게 되어 발생하는 홀의 처리 문제이다. 이를 위해 깊이지도 또는 시차지도의 전처리를 통해 홀의 크기 자체를 줄이기 위한 방안 및 발생된 홀 영역을 주위 신호를 이용하여 채우는 홀 채우기 알고리즘에 대한 연구가 활발히 진행되어 왔다. 일반적으로 홀의 크기를 줄이기 위한 방안으로는 깊이지도에 평활화를 적용하는 전처리 방식들이 주를 이룬다. 깊이지도를 평활화하면 큰 홀의 발생을 막을 수 있다는 장점을 갖게 되지만, 깊이 정보의 손실과 기하학적 왜곡이 발생한다는 단점 또한 동시에 나타난다. 본 논문에서는 이러한 단점을 극복하여 장면 합성 과정에서 발생하는 홀 채우기의 성능을 효과적으로 개선할 수 있는 시차지도 기반의 전처리 알고리즘을 제안한다.

• 한국컴퓨터정보학회논문지
• /
• 제24권9호
• /
• pp.59-67
• /
• 2019

The service composition based on Service-Oriented Architecture(SOA) can make us view various machines or its functionalities in the Web or Internet-of-Things environment as 'service', and efficiently create new value-added services that users want by compositing different services if there is no service to satisfy the client. The service composition problem with respect to behavioral descriptions deals with the automatic synthesis of a coordinator service that controls a set of services to reach a goal state. Despite its importance, however, solving the service composition problem with only partial observations remains to be doubly exponential in the number of variables in service descriptions, rendering any attempts to compute an exact solution for modest size impractical. Toward this challenge, in this paper, we propose novel approximation-based approaches using abstraction methods. We empirically validate that our proposals can solve realistic problems efficiently.