Browsing by Author "Shih, Zen-Chung"

Now showing 1 - 18 of 18

A new image segmentation method for removing background of object movies by learning shape priors
(2006)
Ko, Cheng-Hung
;
Tsai, Yu-Pao
;
Shih, Zen-Chung
;
Hung, Yi-Ping
;
資訊工程學系
This paper proposes a new object movie (OM) segmentation method that incorporates shape priors into the segmentation algorithm. ne shape prior introduced into every image of the OM is learned from the 3D model reconstructed by the volumetric graph cuts. Here, the constraint derived from the discrete medial axis is used to improve the reconstruction algorithm. Our segmentation method requires only a small amount of user intervention, which is to select a subset of acceptable segmentations of the OM after the initial segmentation process. Compared to other techniques, our method provides not only the better segmentation result but also the better 3D reconstruction result.
A nonparametric regression model for virtual humans generation
(2010-03-01)
Chou, Yun-Feng
;
Shih, Zen-Chung
;
資訊工程學系
;
Department of Computer Science
In this paper, we propose a novel nonparametric regression model to generate virtual humans from still images for the applications of next generation environments (NG). This model automatically synthesizes deformed shapes of characters by using kernel regression with elliptic radial basis functions (ERBFs) and locally weighted regression (LOESS). Kernel regression with ERBFs is used for representing the deformed character shapes and creating lively animated talking faces. For preserving patterns within the shapes, LOESS is applied to fit the details with local control. The results show that our method effectively simulates plausible movements for character animation, including body movement simulation, novel views synthesis, and expressive facial animation synchronized with input speech. Therefore, the proposed model is especially suitable for intelligent multimedia applications in virtual humans generation.
Adaptive sampling approach for volumetric shadows in dynamic scenes
(2013-11-01)
Lin, Hsiang-Yu
;
Chang, Chin-Chen
;
Tsai, Yu-Ting
;
Way, Der-Lor
;
Shih, Zen-Chung
Ray marching is an important technique to generate volumetric lighting effects. However, it is very expensive for each pixel on the screen, especially in dynamic scenes. The authors propose an adaptive approach to reduce samples for volumetric shadows in the time domain. In dynamic scenes, shadow volumes of moving objects are created and are rasterised to decide pixels that cannot be reused. The authors use a stencil buffer to maintain the information of screen pixels by recomputing or just using the previous information. Experimental results show that the proposed approach is simple to implement. Moreover, compared to the previous method, the proposed approach achieves a specific speedup and maintains similar visual quality.
All-frequency precomputed radiance transfer using spherical radial basis functions and clustered tensor approximation
(2006-07-01)
Tsai, Yu-Ting
;
Shih, Zen-Chung
;
資訊工程學系
;
Department of Computer Science
This paper introduces a new data representation and compression technique for precomputed radiance transfer (PRT). The light transfer functions and light sources are modeled with spherical radial basis functions (SRBFs). A SRBF is a rotation-invariant function that depends on the geodesic distance between two points on the unit sphere. Rotating functions in SRBF representation is as straightforward as rotating the centers of SRBFs. Moreover, high-frequency signals are handled by adjusting the bandwidth parameters of SRBFs. To exploit inter-vertex coherence, the light transfer functions are further classified iteratively into disjoint clusters, and tensor approximation is applied within each cluster. Compared with previous methods, the proposed approach enables real-time rendering with comparable quality under high-frequency lighting environments. The data storage is also more compact than previous all-frequency PRT algorithms.
An Efficient Structure-Aware Bilateral Texture Filtering for Image Smoothing
(2016-10-01)
Lin, Ting-Hao
;
Way, Der-Lor
;
Shih, Zen-Chung
;
Tai, Wen-Kai
;
Chang, Chin-Chen
Photos contain well-structured and plentiful visual information. Edges are active and expressive stimuli for human visual perception. However, it is hard to separate structure from details because edge strength and object scale are entirely different concepts. This paper proposes a structure-aware bilateral texture algorithm to remove texture patterns and preserve structures. Our proposed method is simple and fast, as well as effective in removing textures. Instead of patch shift, smaller patches represent pixels located at structure edges, and original patches represent the texture regions. Specifically, this paper also improves joint bilateral filter to preserve small structures. Moreover, a windowed inherent variation is adapted to distinguish textures and structures for detecting structure edges. Finally, the proposed method produces excellent experimental results. These results are compared to some results of previous studies. Besides, structure-preserving filtering is a critical operation in many image processing applications. Our proposed filter is also demonstrated in many attractive applications, such as seam carving, detail enhancement, artistic rendering, etc.
An Efficient Structure-Aware Bilateral Texture Filtering for Image Smoothing
(2016-10)
Lin, Ting-Hao
;
Way, Der-Lor
;
Shih, Zen-Chung
;
Tai, Wen-Kai
;
Chang, Chin-Chen
Photos contain well-structured and plentiful visual information. Edges are active and expressive stimuli for human visual perception. However, it is hard to separate structure from details because edge strength and object scale are entirely different concepts. This paper proposes a structure-aware bilateral texture algorithm to remove texture patterns and preserve structures. Our proposed method is simple and fast, as well as effective in removing textures. Instead of patch shift, smaller patches represent pixels located at structure edges, and original patches represent the texture regions. Specifically, this paper also improves joint bilateral filter to preserve small structures. Moreover, a windowed inherent variation is adapted to distinguish textures and structures for detecting structure edges. Finally, the proposed method produces excellent experimental results. These results are compared to some results of previous studies. Besides, structure-preserving filtering is a critical operation in many image processing applications. Our proposed filter is also demonstrated in many attractive applications, such as seam carving, detail enhancement, artistic rendering, etc.
Animating Characters Using Nonparametric Regression
(2008)
Chou, Yun-Feng
;
Shih, Zen-Chung
;
資訊工程學系
;
Department of Computer Science
In this paper, we propose an image deformation technique using nonparametric regression to animate characters in a still image for multimedia applications. The proposed approach effectively produces a sequence of contiguous frames in an animation. It automatically generates deformed shapes by using elliptic radial basis functions (ERBFs) and locally weighted regression (LOESS). ERBFs are used for representing the deformed character's shapes in synthesized frames. For preserving the pattern within a shape, LOESS is applied to fit the detail with local control. Furthermore, the results show the synthesized frames without unnatural distortion.
Automatic geometric and photometric calibration for tiling multiple projectors with a pan-tilt-zoom camera
(2006)
Tsai, Yu-Pao
;
Wu, Yen-Nien
;
Liao, Shou-Chun
;
Shih, Zen-Chung
;
Hung, Yi-Ping
Research on creating a large, high-resolution, low-cost display system has become increasingly important due to the growing desire in many fields for bigger and better displays. The goal of this research is to build a seamless large-scale display system by tiling multiple projectors with the help of a pan-tilt-zoom camera. In order to achieve this goal, we took two tasks into consideration: geometric calibration and photometric calibration. Compared to the previous work, our method for geometric calibration is more accurate, thanks to the much higher resolution images acquired by combining several zoom-in images and doing lens correction for the camera at first. For photometric calibration, we achieve color uniformity among projectors by utilizing the same PTZ camera, which is calibrated once with a colorimeter in a factory. Furthermore, we adopted the technique of producing a high dynamic range image from several images of different exposures to increase the measurement accuracy of the camera. In our experiments, the average error of photometric measurement achieved by our method is less than the mean perceptibility tolerance. Our method has great potential for many applications that require large and high-resolution displays.
Background removal of multiview images by learning shape priors
(2007-10-01)
Tsai, Yu-Pao
;
Ko, Cheng-Hung
;
Hung, Yi-Ping
;
Shih, Zen-Chung
;
資訊工程學系
Image-based rendering has been successfully used to display 3-D objects for many applications. A well-known example is the object movie, which is an image-based 3-D object composed of a collection of 2-D images taken from many different viewpoints of a 3-D object. In order to integrate image-based 3-D objects into a chosen scene (e.g., a panorama), one has to meet a hard challenge-to efficiently and effectively remove the background from the foreground object. This problem is referred to as multiview images (MVIs) segmentation. Another task requires MVI segmentation is image-based 3-D reconstruction using multiview images. In this paper, we propose a new method for segmenting MVI, which integrates some useful algorithms, including the well-known graph-cut image segmentation and volumetric graph-cut. The main idea is to incorporate the shape prior into the image segmentation process. The shape prior introduced into every image of the MVI is extracted from the 3-D model reconstructed by using the volumetric graph cuts algorithm. Here, the constraint obtained from the discrete medial axis is adopted to improve the reconstruction algorithm. The proposed MVI segmentation process requires only a small amount of user intervention, which is to select a subset of acceptable segmentations of the MVI after the initial segmentation process. According to our experiments, the proposed method can provide not only good MVI segmentation, but also provide acceptable 3-D reconstructed models for certain less-demanding applications.
Clip Space Sample Culling for Motion Blur and Defocus Blur
(2015-05-01)
Wu, Yi-Jeng
;
Way, Der-Lor
;
Tsai, Yu-Ting
;
Shih, Zen-Chung
;
多媒體工程研究所
Motion blur and defocus blur are two common visual effects for rendering realistic camera images. This paper presents a novel clip space culling for stochastic rasterization to render motion and defocus blur effects. Our proposed algorithm reduces the sample coverage using the clip space information in camera lens domain (UV) and time domain (T). First, samples outside the camera lens were culled in stage I using the linear relationship between camera lens and vertex position. Second, samples outside the time bounds were culled in stage II using the triangle similarity in clip space to find the intersection time. Each pixel was computed within two linear bounds only once. Our method achieves good sample test efficiency with low computation cost for real-time stochastic rasterization. Finally, the proposed method is demonstrated by means of various experiments, and a comparison is made with previous works. Our algorithm was able to handle these two blur effects simultaneously and performed better than others did.
Comic character animation using Bayesian estimation
(2011-09-01)
Chou, Yun-Feng
;
Shih, Zen-Chung
;
資訊工程學系
;
Department of Computer Science
The motion of comic characters includes different types of movements, such as walking or running. In a comic, a movement may be described by a series of non-continuous poses in a sequence of contiguous frames. Each pose exists in a frame. We synthesize an animation according to still comic frames. In this paper, we propose a model to analyze time series of a character's motion using the non-parametric Bayesian approach. Then we can automatically generate a sequence of motions by using the estimated time series. Experimental results show that the built time series model best matches the given frames. Furthermore, unnatural distortions of the results are minimized. Copyright (C) 2011 John Wiley & Sons, Ltd.
Computer-generated Chinese color ink paintings
(2006-10-01)
Way, Der-Lor
;
Lin, Wei-Jin
;
Shih, Zen-Chung
;
資訊工程學系
;
Department of Computer Science
Chinese color ink painting is a traditional art form, a non-photorealistic rendering, that is over three thousand years old. Simulating the behavior of Chinese ink is challenging. Various artistic effects of color ink diffusion are analyzed, and a scheme presents how they can be simulated automatically for their computer-generated simulation. The proposed method simulates various tonal expressions on different papers. by employing a Kubelka-Munk model to simulate optical effects. Elucidation of the effect of mixing simulated strokes with different brushes is a significant contribution of the proposed method. Finally, results of this study demonstrate the effectiveness of an interactive painting system. Also, results are compared with genuine ink paintings.
Generation of Stereo Images Based on a View Synthesis Network
(2020-05-01)
Lo, Yuan-Mau
;
Chang, Chin-Chen
;
Way, Der-Lor
;
Shih, Zen-Chung
;
多媒體工程研究所
The conventional warping method only considers translations of pixels to generate stereo images. In this paper, we propose a model that can generate stereo images from a single image, considering both translation as well as rotation of objects in the image. We modified the appearance flow network to make it more general and suitable for our model. We also used a reference image to improve the inpainting method. The quality of images resulting from our model is better than that of images generated using conventional warping. Our model also better retained the structure of objects in the input image. In addition, our model does not limit the size of the input image. Most importantly, because our model considers the rotation of objects, the resulting images appear more stereoscopic when viewed with a device.
Inner engraving for the creation of a balanced LEGO sculpture
(2016-05)
Hong, Jhen-Yao
;
Way, Der-Lor
;
Shih, Zen-Chung
;
Tai, Wen-Kai
;
Chang, Chin-Chen
LEGO is a globally popular toy composed of colorful interlocking plastic bricks that can be assembled in many ways; however, this special feature makes designing a LEGO sculpture particularly challenging. Building a stable sculpture is not easy for a beginner; even an experienced user requires a good deal of time to build one. This paper provides a novel approach to creating a balanced LEGO sculpture for a 3D model in any pose, using centroid adjustment and inner engraving. First, the input 3D model is transformed into a voxel data structure. Next, the model\'s centroid is adjusted to an appropriate position using inner engraving to ensure that the model stands stably. A model can stand stably without any struts when the center of mass is moved to the ideal position. Third, voxels are merged into layer-by-layer brick layout assembly instructions. Finally, users will be able to build a LEGO sculpture by following these instructions. The proposed method is demonstrated with a number of LEGO sculptures and the results of the physical experiments are presented.
K-Clustered Tensor Approximation: A Sparse Multilinear Model for Real-Time Rendering
(2012-05-01)
Tsai, Yu-Ting
;
Shih, Zen-Chung
;
資訊工程學系
;
Department of Computer Science
With the increasing demands for photo-realistic image synthesis in real time, we propose a sparse multilinear model, which is named K-Clustered Tensor Approximation (K-CTA), to efficiently analyze and approximate large-scale multidimensional visual datasets, so that both storage space and rendering time are substantially reduced. K-CTA not only extends previous work on Clustered Tensor Approximation (CTA) to exploit inter-cluster coherence, but also allows a compact and sparse representation for high-dimensional datasets with just a few low-order factors and reduced multidimensional cluster core tensors. Thus, K-CTA can be regarded as a sparse extension of CTA and a multilinear generalization of sparse representation. Experimental results demonstrate that K-CTA can accurately approximate spatially varying visual datasets, such as bidirectional texture functions, view-dependent occlusion texture functions, and biscale radiance transfer functions for efficient rendering in real-time applications.
Modeling Bidirectional Texture Functions with Multivariate Spherical Radial Basis Functions
(2011-07-01)
Tsai, Yu-Ting
;
Fang, Kuei-Li
;
Lin, Wen-Chieh
;
Shih, Zen-Chung
;
資訊工程學系
This paper presents a novel parametric representation for bidirectional texture functions. Our method mainly relies on two original techniques, namely, multivariate spherical radial basis functions (SRBFs) and optimized parameterization. First, since the surface appearance of a real-world object is frequently a mixed effect of different physical factors, the proposed sum-of-products model based on multivariate SRBFs especially provides an intrinsic and efficient representation for heterogenous materials. Second, optimized parameterization particularly aims at overcoming the major disadvantage of traditional fixed parameterization. By using a parametric model to account for variable transformations, the parameterization process can be tightly integrated with multivariate SRBFs into a unified framework. Finally, a hierarchical fitting algorithm for bidirectional texture functions is developed to exploit spatial coherence and reduce computational cost. Our experimental results further reveal that the proposed representation can easily achieve high-quality approximation and real-time rendering performance.
Origami Pop-up Card Generation from 3D Models Using a Directed Acyclic Graph
(2013-11-01)
Way, Der-Lor
;
Tsai, Yi-Shan
;
Shih, Zen-Chung
;
資訊工程學系
;
Department of Computer Science
Origami is a paper art used to create three-dimensional (3D) objects by cutting and folding a single sheet of paper. Origami is labor-intensive and requires a high skill level to generate two-dimensional (2D) objects that pop-up into realistic 3D objects. However, this special feature makes designing an origami architecture procedure challenging. This paper provides a novel algorithm to create an origami paper card from a 3D model with a user-specified folding line. The algorithm segments the 2D shape from a 3D model and creates layers of the pop-up paper card using a directed acyclic graph. After applying layers to the layout, the algorithm creates connections between layers, and then outputs the origami layout. Based on a directed acyclic graph, the algorithm computes a class of paper architectures containing two sets of layers and connections that approximate the input geometry while guaranteeing that a pop up card is physically realizable. The proposed method is demonstrated with a number of paper pop-ups, and physical experimental results are presented.
The simulation of tsunami wave propagation
(2007)
Kuo, Yen-Ting
;
Shih, Zen-Chung
;
多媒體工程研究所
;
Institute of Multimedia Engineering
The tsunami which happened in 2004 has made lots of damages, and people saw the video from TV, they finally know how terrible the tsunami is. However, the movements of tsunami waves are not like those which are shown in Hollywood movies. In ocean engineering, they only simulate the surface of the tsunami wave movements, and the simulations are not rendered in a realistic way. In computer graphics, the ocean simulations often show the results which focus on the small movement on the ocean surface. In this thesis, we want to combine advantages in these two domains. We hope that we can simulate the tsunami wave propagation by physically-correct equations developed in ocean engineering and we render the simulated scene by the techniques developed in computer graphics to make it realistic. And we hope that our simulation system can make people having more understanding about tsunami waves.