• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.243-245
• /
• 2022

다양한 분야에서 심층 신경망 기반 모델이 사용되면서 뛰어난 성능을 보이고 있다. 그러나 기계학습 모델의 오작동을 유도하는 적대적 공격(adversarial attack)에 의해 심층 신경망 모델의 취약성이 드러났다. 보안 분야에서는 이러한 취약성을 보완하기 위해 의도적으로 모델을 공격함으로써 모델의 강건함을 검증한다. 현재 2D 이미지에 대한 적대적 공격은 활발한 연구가 이루어지고 있지만, 3D 데이터에 대한 적대적 공격 연구는 그렇지 않은 실정이다. 본 논문에서는 뉴럴 렌더링(neural rendering)과 적대적 공격, 그리고 3D 표현에 적대적 공격을 적용한 연구를 조사해 이를 통해 추후 뉴럴 렌더링에서 일어나는 적대적 공격 연구에 도움이 될 것을 기대한다.

• Journal of Korea Game Society
• /
• v.7 no.3
• /
• pp.59-66
• /
• 2007

Ray tracing is one of the classical global illumination methods to generate a photo-realistic rendering image with various lighting effects such as reflection and refraction. However, there are some restrictions on real-time applications because of its computation load. In order to overcome these limitations, many researches of the ray tracing based on GPU (Graphics Processing Unit) have been presented up to now. In this paper, we implement the ray tracing algorithm by J. Purcell and combine it with two methods in order to improve the rendering performance for interactive applications. First, intersection points of the primary ray are determined efficiently using rasterization on graphics hardware. We then construct the acceleration structure of 3D objects to improve the rendering performance. There are few researches on a detail analysis of improved performance by these considerations in ray tracing rendering. We compare the rendering system with environment mapping based on GPU and implement the wireless remote rendering system. This system is useful for interactive applications such as the realtime composition, augmented reality and virtual reality.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.4
• /
• pp.1171-1187
• /
• 2012

A depth adjustment method for visual fatigue reduction for depth-image-based rendering (DIBR) system is proposed. One important aspect of the method is that no calibration parameters are needed for adjustment. By analyzing 3D image warping, the perceived depth is expressed as a function of three adjustable parameters: virtual view number, scale factor and depth value of zero parallax setting (ZPS) plane. Adjusting these three parameters according to the proposed parameter modification algorithm when performing 3D image warping can effectively change the perceived depth of stereo pairs generated in DIBR system. As the depth adjustment is performed in simple 3D image warping equations, the proposed method is facilitative for hardware implementation. Experimental results show that the proposed depth adjustment method provides an improvement in visual comfort of stereo pairs as well as generating comfortable stereoscopic images with different perceived depths that people desire.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.142-146
• /
• 2023

We present a method for generating 3D structures and rendering objects by combining VAE (Variational Autoencoder) and GAN (Generative Adversarial Network). This approach focuses on generating and rendering 3D models with improved quality using residual learning as the learning method for the encoder. We deep stack the encoder layers to accurately reflect the features of the image and apply residual blocks to solve the problems of deep layers to improve the encoder performance. This solves the problems of gradient vanishing and exploding, which are problems when constructing a deep neural network, and creates a 3D model of improved quality. To accurately extract image features, we construct deep layers of the encoder model and apply the residual function to learning to model with more detailed information. The generated model has more detailed voxels for more accurate representation, is rendered by adding materials and lighting, and is finally converted into a mesh model. 3D models have excellent visual quality and accuracy, making them useful in various fields such as virtual reality, game development, and metaverse.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.4
• /
• pp.335-342
• /
• 2012

3D point cloud is widely used in Architecture, Civil Engineering, Medical, Computer Graphics, and many other fields. Due to the improvement of 3D laser scanner, a massive 3D point cloud whose gigantic file size is bigger than computer's memory requires efficient preprocessing and visualization. We suggest a data structure to solve the problem; a 3D point cloud is gradually subdivided by arbitrary-sized cube grids structure and corresponding point cloud subsets generated by the center of each grid cell are achieved while preprocessing. A massive 3D point cloud file is tested through two algorithms: QSplat and ours. Our algorithm, grid-based, showed slower speed in preprocessing but performed faster rendering speed comparing to QSplat. Also our algorithm is further designed to editing or segmentation using the original coordinates of 3D point cloud.

• Journal of the Korean Society of Visualization
• /
• v.1 no.2
• /
• pp.58-70
• /
• 2003

Meteorological data contains observation and numerical weather prediction model output data. The computerized analysis and visualization of meteorological data often requires very high computing capability due to the large size and complex structure of the data. Because the meteorological data is frequently formed in multi-variables, 3-dimensional and time-series form, it is very important to visualize and analyze the data in 3D spatial domain in order to get more understanding about the meteorological phenomena. In this research, we developed interactive 3-dimensional visualization techniques for visualizing meteorological data on a PC environment such as volume rendering, iso-surface rendering or stream line. The visualization techniques developed in this research are expected to be effectively used as basic technologies not only for deeper understanding and more exact prediction about meteorological environments but also for scientific and spatial data visualization research in any field from which three dimensional data comes out such as oceanography, earth science, and aeronautical engineering.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.666-669
• /
• 2005

본 논문에서는 3차원 형태로 체적 데이터를 효율적으로 랜더링 하기 위해서, 체적 데이터의 특징점을 추출하고 이를 이용하여 3차원 형태로 복원한다. 여기서, 3D Point(Vertext)를 이용하여 체적 데이터를 랜더링하고자 하여 체적소들에 대해 특정한 3D Points 추출하는 PEF 과정과 랜더링 과정을 담당하는 정점 변환 파이프라인 과정을 제안한다. 일반적으로, 고화질의 광선 추적 랜더링 처리의 경우 계샨량이 많아 그 만큼 랜더링 속도가 떨어져 체적에 대한 다른 ?A너링 기법들이 많이 제안되고 있지만, 본 논문은 다른 각도로의 접근하고자 하여, 기존의 광선 추적에 비해 저화질과 매끄럽지 않는 영상을 나타내지만, 추출된 데이터만 고려하기 때문에 계샨량을 많이 줄일 수 있어 처리속도가 개선되어 졌을 볼 수가 있다. 또한, 본 논문에서 기존의 광선 추적 기법에서 표현하는 회전, 절단, 축소/확대의 기능을 그대로 OpenGL을 이용하여 본 논문에서 제안한 처리 단계로 하여 3차원 랜더링 프로그램 제작 하였다.

• Proceedings of the Korea Contents Association Conference
• /
• 2015.05a
• /
• pp.327-328
• /
• 2015

디지털시대에서 미국카툰시장은 3D 디지털 기법을 충분히 활용하여 마치 실사 같은 영화(Photo realistic movie)를 제작하는 한편. 일본의 경우는 그들만의 독특한 전통 셀 애니메이션(cell animation) 형식을 3D CG 기술과 결합하여 새로운 제작방식의 애니메이션을 제시하고 있다. 본 연구는 일본 2D 애니메이션에서 제작 방식을 유지해야 할 당위성을 카툰 렌더링 3D의 제작방식에 도입하여, 융합한 사례 분석을 통해 2D 애니메이션의 필요성과 중요성을 제시하려 한다.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.93-103
• /
• 2023

The problem of reconstructing three-dimensional models of people and objects from color and depth images captured by low-cost RGB-D cameras has long been an active research area in computer graphics. Color and depth images captured by low-cost RGB-D cameras are represented as point clouds in three-dimensional space, which correspond to discrete values in a continuous three-dimensional space and require additional surface reconstruction compared to rendering using polygonal models. In this paper, we propose an effective ray-tracing based technique for visualizing point clouds rather than polygonal models. In particular, our method shows the possibility of an effective rendering method even in mobile environment which has limited performance due to processor heat and lack of battery.

• Journal of Korea Game Society
• /
• v.6 no.4
• /
• pp.55-61
• /
• 2006

Graphics rendering pipeline (application, geometry, and rasterizer) is the core of real-time graphics which is the most important functionality for computer games. Usually this rendering process is completed by both the CPU and the GPU, and a bottleneck can be located either in the CPU or the GPU. This paper focuses on reducing the bottleneck between the CPU and the GPU. We are proposing a method for improving the performance of parallel processing for real-time graphics rendering by separating the CPU operations (usually performed using a thread) into two parts: pure CPU operations and operations related to the GPU, and let them operate in parallel. This allows for maximizing the parallelism in processing the communication between the CPU and the GPU. Some experiments lead us to confirm that our method proposed in this paper can allow for faster graphics rendering. In addition to our method of using a dedicated thread for GPU related operations, we are also proposing an algorithm for balancing the graphics pipeline using the idle time due to the bottleneck. We have implemented the two methods proposed in this paper in our networked 3D game engine and verified that our methods are effective in real systems.