Browsing by Author "Chuang, Jung-Hong"

Now showing 1 - 20 of 23

A Simple Yet Effective User Controllable Mesh Simplification
(2013-05-01)
Ho, Tan-Chi
;
Chuang, Jung-Hong
;
資訊工程學系
;
Department of Computer Science
Mesh simplification has become a key ingredient for real-time graphics applications. However, practitioners have found that automatic simplification methods usually fail to produce satisfactory result when models of very low polygon count are desired. This is due to the fact that existing methods take no semantic or functional metric into account, and moreover, each error metric proposed previously has its own strength and weakness. In this paper, we propose a user-controllable mesh simplification framework that allows users to achieve a predictable resolution improvement in selected regions of a simplified mesh derived by using any error metric. The framework consists of two stages. The first stage employs weighting schemes that allow users to refine unsatisfactory regions to a user-expected resolution. The second stage is a local refinement aiming to provide a user-guided fine-tune to recover local sharp features. Two weighting schemes, namely uniform weighting and nonuniform weighting, are proposed. In uniform weighting scheme, a weight value is applied to all original mesh vertices in a selected region, resulting in a uniform improvement on vertex resolution in the region, while in the nonuniform weighting scheme varying weights are applied to vertices in a selected region and obtain a nonuniform resolution improvement in the region. Different from the previous user-assisted simplification methods that reorder the collapsing sequence indirectly by weighting the collapsing cost of edges, the two proposed weighting schemes directly reorder the edge collapsing sequence, ensuring a predictable resolution improvement in the selected regions. Moreover, the proposed weighting schemes are independent on error metric used for simplification and ensure the same resolution improvement when a weighting value is applied to simplified meshes with different resolutions.
A Skeleton-Based Approach for Consistent Segmentation Transfer
(2014-07-01)
Wong, Sai-Keung
;
Yang, Jau-An
;
Ho, Tan-Chi
;
Chuang, Jung-Hong
;
資訊工程學系
We present a skeleton-based approach for mapping consistently a segmentation of a source mesh to a target mesh. The source and target meshes are semantically similar but their geometries may be different. We assume that the segmentation of the source mesh and the skeleton correspondence between the meshes are provided. Our method first establishes the skeleton-boundary correspondence and then performs the boundary transfer procedure. The skeleton-boundary correspondence is useful for computing approximately the target boundaries. The boundary transfer procedure aims to produce the segment boundaries of the target mesh such that their geometric details are consistent to the ones of the corresponding source segment boundaries. We have applied our method for various models and compared with the state-of-the-art techniques. Our method computes segment boundaries of the target mesh which are similar to the ones of the source mesh.
ADVERSARIAL GENERATION OF DEFENSIVE TRAJECTORIES IN BASKETBALL GAMES
(2018-01-01)
Chen, Chieh-Yu
;
Lai, Wenze
;
Hsieh, Hsin-Ying
;
Wang, Yu-Shuen
;
Peng, Wen-Hsiao
In this paper, we present a method to generate realistic trajectories of defensive players in a basketball game based on the ball and the offensive team's movements. We train on the NBA dataset a conditional generative adversarial network that learns spatio-temporal interactions between players' movements. The network consists of two components: a generator that takes as input a latent noise vector and the offensive team's trajectories to generate defensive trajectories; and a discriminator that evaluates the realistic degree of the generated results. Our system allows players and coaches to simulate how the opposing team will react to a newly developed offensive strategy for evaluating its effectiveness. Experimental results demonstrate the feasibility of the proposed algorithm.
An Artist Friendly Material Design System
(2017-03-01)
Huang, Tsung-Shian
;
Liao, Jen-Hao
;
Lin, Wen-Chieh
;
Chuang, Jung-Hong
;
資訊工程學系
Material design is an important task in game and animation industry. It often requires artist's great efforts to create an elaborate material. Although several successful material editing systems already exist, it is still hard for artists to design a material on their own since these systems usually have neither an intuitive and sufficiently sophisticated material representation nor an artist-friendly editing interface. In this paper, we propose a simple material creation flow and develop a material design system based on an intuitive material representation. With the system, an artist can bring their creativity into play on designing materials that are realistic or imaginary.
An efficient caching-based rendering of translucent materials
(2007-01-01)
Keng, Shih-Ling
;
Lee, Wang-Yeh
;
Chuang, Jung-Hong
;
資訊工程學系
;
Department of Computer Science
This paper presents an efficient caching-based rendering technique for translucent materials. The proposed caching scheme, inspired by the irradiance caching method, is integrated into a hierarchical rendering technique for translucent materials. We propose a split-disk model to determine the cache distribution and derive the subsurface illuminance gradient used for interpolation by reformulating the equation of dipole diffusion approximation as a 3D convolution process. Our experiments show that only a few caches are required to interpolate the entire image, while the visual difference is negligible. The speedup could be achieved up to one order of magnitude.
BasketballGAN: Generating Basketball Play Simulation Through Sketching
(2019-01-01)
Hsieh, Hsin-Ying
;
Chen, Chieh-Yu
;
Wang, Yu-Shuen
;
Chuang, Jung-Hong
;
交大名義發表
We present a data-driven basketball set play simulation. Given an offensive set play sketch, our method simulates potential scenarios that may occur in the game. The simulation provides coaches and players with insights on how a given set play can be executed. To achieve the goal, we train a conditional adversarial network on NBA movement data to imitate the behaviors of how players move around the court through two major components: a generator that learns to generate natural player movements based on a latent noise and a user sketched set play; and a discriminator that is used to evaluate the realism of the basketball play. To improve the quality of simulation, we minimize 1.) a dribbler loss to prevent the ball from drifting away from the dribbler; 2.) a defender loss to prevent the dribbler from not being defended; 3.) a ball passing loss to ensure the straightness of passing trajectories; and 4) an acceleration loss to minimize unnecessary players' movements. To evaluate our system, we objectively compared real and simulated basketball set plays. Besides, a subjective test was conducted to judge whether a set play was real or generated by our network. On average, the mean correct rates to the binary tests were 56.17 %. Experiment results and the evaluations demonstrated the effectiveness of our system.
Design and Initial Evaluation of a VR based Immersive and Interactive Architectural Design Discussion System
(2020-01-01)
Hsu, Ting-Wei
;
Tsai, Ming-Han
;
Babu, Sabarish, V
;
Hsu, Pei-Hsien
;
Chang, Hsuan-Ming
Design discussion is a very important course in architecture education. In this paper, we developed a VR based architecture design discussion system that allows members to visualize and discuss the architectural models and to modify the models during discussion. Since the system is designed to work on top of Rhinoceros and Grasshopper, the object database is updated right after the object modification. Members communicate via voice, object manipulations, and mid-air sketching as well as on-surface sketching in the virtual environment. Several tools have been designed to enhance the sense of presence and to make the discussion more effective. We also developed a rollback mechanism to help users intuitively and quickly revert to a previous state of discussion to make some changes or to start a new direction of discussion. To evaluate the system, we conducted an initial user study with 14 participants to assess the user experience, user impression and effectiveness of the system. The feedback from participants were positive and suggested that the system could be effective and useful for supporting architecture design discussion.
Exemplar-based freckle retouching and skin tone adjustment
(2019-02-01)
Lin, Tsung-Ying
;
Tsai, Yu-Ting
;
Huang, Tsung-Shian
;
Lin, Wen-Chieh
;
Chuang, Jung-Hong
This paper presents a novel system for freckle retouching and skin tone adjustment based on a set of exemplar image pairs obtained before and after cosmetic laser therapy. Our key observation is that cosmetic laser therapy relies on decomposing and adjusting melanin and hemoglobin to change skin appearance, and the reflectance properties of the two pigments can greatly influence human skin color. We thus retouch freckles and adjust skin tone in a query image by changing the densities of melanin and hemoglobin to match the variation of those in the exemplar image pairs. Based on the proposed system, we can easily and intuitively generate an output image that looks similar to the results of cosmetic laser therapy. Our system also can detect more skin flaws and define their regions more accurately than previous retouching methods. (C) 2018 Elsevier Ltd. All rights reserved.
Fire synthesis using basis fires and design
(2017-03-01)
Wong, Sai-Keung
;
Chang, Tse-Ching
;
Ho, Tan-Chi
;
Chuang, Jung-Hong
;
交大名義發表
In this paper, we present an approach to use basis fires to design and synthesize fires in desired shapes and motions. In the preprocessing stage, each basis fire is simulated based on a physics-based fire simulator with a specific simulation configuration. The pathlines and temperatures of the basis fires are stored in a database. In the fire design stage, a user inputs a sequence of curves which represent the desired shapes of fires. In the fire synthesis stage, we use a least-square fitting method to fit the curves using the pathlines and temperatures of the basis fires. In the fire animation stage, we adopt a modified motion graph for animating the synthesized fires. We have applied our approach to synthesize fires with different shapes and motions. Experimental results show that our approach is easy to use and it can produce fires with desired shapes in an intuitive manner. The synthesized fire can be animated at real-time rates.
Generating Defensive Plays in Basketball Games
(2018-01-01)
Chen, Chieh-Yu
;
Lai, Wenze
;
Hsieh, Hsin-Ying
;
Zheng, Wen-Hao
;
Wang, Yu-Shuen
In this paper, we present a method to generate realistic defensive plays in a basketball game based on the ball and the offensive team's movements. Our system allows players and coaches to simulate how the opposing team will react to a newly developed offensive strategy for evaluating its effectiveness. To achieve the aim, we train on the NBA dataset a conditional generative adversarial network that learns spatio-temporal interactions between players' movements. The network consists of two components: a generator that takes a latent noise vector and the offensive team's trajectories as input to generate defensive team's trajectories; and a discriminator that evaluates the realistic degree of the generated results. Since a basketball game can be easily identified as fake if the ball handler, who is not defended, does not shoot the ball or cut into the restricted area, we add the wide open penalty to the objective function to assist model training. To evaluate the results, we compared the similarity of the real and the generated defensive plays, in terms of the players' movement speed and acceleration, distance to defend ball handlers and non-ball handlers, and the frequency of wide open occurrences. In addition, we conducted a user study with 59 participants for subjective tests. Experimental results show the high fidelity of the generated defensive plays to real data and demonstrate the feasibility of our algorithm.
Immersive VR Environment for Architectural Design Education
(2017-01-01)
Tsou, Chia-Hung
;
Hsu, Ting-Wei
;
Lin, Chun-Heng
;
Tsai, Ming-Han
;
Hsu, Pei-Hsien
In tradition architectural design education, instructor and students share and discuss their ideas through drawings and models. Physical models are hard to be modified during discussion, and it is difficult to view the interior spaces. Drawings, including plans, elevations and sections, are generally used as a medium for the purpose of presentation and discussion. We propose an integrated system to support architectural design education, in which multiple users can not only explore and discuss 3D designs in a VR environment, but also manipulate 3D elements. This system also integrates procedural 3D modeling, providing users with the capability of modifying 3D designs in real-time through adjustments of parameters.
Interactive Lighting Design with Hierarchical Light Representation
(2013-06-01)
Lin, Wen-Chieh
;
Huang, Tsung-Shian
;
Ho, Tan-Chi
;
Chen, Yueh-Tse
;
Chuang, Jung-Hong
Lighting design plays a crucial role in indoor lighting design, computer cinematograph and many other applications. Computer-assisted lighting design aims to find a lighting configuration that best approximates the illumination effect specified by designers. In this paper, we present an automatic approach for lighting design, in which discrete and continuous optimization of the lighting configuration, including the number, intensity, and position of lights, are achieved. Our lighting design algorithm consists of two major steps. The first step estimates an initial lighting configuration by light sampling and clustering. The initial light clusters are then recursively merged to form a light hierarchy. The second step optimizes the lighting configuration by alternatively selecting a light cut on the light hierarchy to determine the number of representative lights and optimizing the lighting parameters using the simplex method. To speed up the optimization computation, only illumination at scene vertices that are important to rendering are sampled and taken into account in the optimization. Using the proposed approach, we develop a lighting design system that can compute appropriate lighting configurations to generate the illumination effects iteratively painted and modified by a designer interactively.
Interactive Visual Analysis of Browsing and Authoring Behaviors in Web Media
(2015)
Kuan, Yen-Ting
;
Tai, Ming-Hung
;
Kuan, Hsuan-Hao
;
Ho, Tan-Chi
;
Wang, Yu-Shuen
Web media is becoming popular nowadays for people to read news or articles. It is interesting and important for the web media providers to learn the browsing behaviors of their readers and authors. In this paper, we present a visual analytics system for discovering the browsing and authoring behaviors in web media based on users web page clickstream data. Our system provides multiple views of visualization with user interaction, including a scatter plot providing an overview to help analysts locate data of interest, and a force-directed graph for investigating relations between data entities. Interesting behaviors have been explored and found by using the proposed multiple views system.
Lighting and Foggy Effect Transfer
(2017-09-01)
Huang, Tsung-Shian
;
Huang, Fu-Hsi
;
Lin, Wen-Chieh
;
Chuang, Jung-Hong
;
資訊工程學系
Participating media, e.g., fog and smoke, play an important role in computer animation and games. They influence the atmosphere of scenes by inducing some special lighting effects, such as the distant blur, glows, and god rays. To design the lighting effects in a scene with fog or smoke, users usually need to tune many parameters to achieve their goal. In this paper, we propose a method that aims to transfer the desired lighting and homogeneous foggy effects in target images, including glow, god rays, and fog attributes, to a 3D scene by solving an inverse problem. The experimental results show that our approach is effective, intuitive, and user-friendly.
Line Drawing Simplification by Stroke Translation and Combination
(2014)
Chien, Yun
;
Lin, Wen-Chieh
;
Huang, Tsung-Shian
;
Chuang, Jung-Hong
;
資訊工程學系
In this paper, we propose a new algorithm for simplifying line drawing sketches. First, we segment the strokes at the points of large curvature if desired. Then, we perform a low-pass filter and use the result to assign a weight to every stroke. The strokes are moved to the position of the higher weight. After that, we find the stroke pairs and combine them to reduce the total number of the strokes, resulting in a cleaner line drawing art. This system also cuts down the disordered and confusing small strokes and combines them to form long strokes.
Multi-resolution volume rendering of large time-varying data using video-based compression
(2008)
Ko, Chia-Lin
;
Liao, Horng-Shyang
;
Wang, Tsai-Pei
;
Fu, Kuang-Wei
;
Lin, Ching-Yao
We present a new framework that combines the hierarchical multi-resolution representation with video-based compression to manage and render large scale time-varying data. In the preprocessing step, the proposed method first constructs a multi-resolution hierarchy using octree structure for each individual time step, and then applies a motion-compensation-based prediction to compress the octree nodes. During rendering stage, the data is decompressed on-the-fly and rendered using hardware texture mapping. The proposed approach eliminates the hierarchical decompression dependency commonly found in the conventional hierarchical wavelet representation methods, which leads to a more efficient reconstruction of data along the time axis. The system provides the user with a spatial region-of-interest (ROI) to adjust the spatial level-of-detail (LOD) selection, and a temporal ROI which is a sub-region only for frequent update during playback. With a suitable control of both ROIs, our system can reach an interactive playback frame rate. This allows the user to observe the dynamic nature of large time-varying data sets.
Physically based cosmetic rendering
(2013-05-01)
Huang, Cheng-Guo
;
Huang, Tsung-Shian
;
Lin, Wen-Chieh
;
Chuang, Jung-Hong
;
資訊工程學系
Simulating realistic makeup effects is one of the important research issues in the 3D facial animation and cosmetic industry. Existing approaches based on image processing techniques, such as warping and blending, have been mostly applied to transfer one's makeup to another's. Although these approaches are intuitive and need only makeup images, they have some drawbacks, for example, distorted shapes and fixed viewing and lighting conditions. In this paper, we propose an integrated approach, which combines the KubelkaMunk model and a screen-space skin rendering approach, to simulate 3D makeup effects. The KubelkaMunk model is used to compute total transmittance when light passes through cosmetic layers, whereas the screen-space translucent rendering approach simulates the subsurface scattering effects inside human skin. The parameters of KubelkaMunk model are obtained by measuring the optical properties of different cosmetic materials, such as foundations, blushes, and lipsticks. Our results demonstrate that the proposed approach is able to render realistic cosmetic effects on human facial models, and different cosmetic materials and styles can be flexibly applied and simulated in real time. Copyright (c) 2013 John Wiley & Sons, Ltd.
Real-time translucent rendering using GPU-based texture space importance sampling
(2008-04-01)
Chang, Chih-Wen
;
Lin, Wen-Chieh
;
Ho, Tan-Chi
;
Huang, Tsung-Shian
;
Chuang, Jung-Hong
We present a novel approach for real-time rendering of translucent surfaces. The computation of subsurface scattering is performed by first converting the integration over the 3D model surface into an integration over a 2D texture space and then applying importance sampling based on the irradiance stored in the texture. Such a conversion leads to a feasible GPU implementation and makes real-time frame rate possible. Our implementation shows that plausible images can be rendered in real time for complex translucent models with dynamic light and material properties. For objects with more apparent local effect, our approach generally requires more samples that may downgrade the frame rate. To deal with this case, we decompose the integration into two parts, one for local effect and the other for global effect, which are evaluated by the combination of available methods [DS03, MKB* 03a] and our texture space importance sampling, respectively. Such a hybrid scheme is able to steadily render the translucent effect in real time with a fixed amount of samples.
Simulating painted appearance of BTF materials
(2018-03-01)
Chen, Ta-En
;
Huang, Tsung-Shian
;
Lin, Wen-Chieh
;
Chuang, Jung-Hong
;
資訊工程學系
Bidirectional texture function (BTF) provides a realistic representation for real-world materials; however, the representation does not allow users to append additional rendering effects to the BTF data in a simple and effective way. In this paper, we present an approach for generating the painted appearance on a material that is represented by a BTF. We first convert a BTF into a physical representation composed of a height-field and a spatially varying bidirectional reflectance distribution function (SVBRDF). This representation allows us to simulate the appearance of paints on the surface of a material by computing the reflectance and the height field of the painted material. During rendering, we combine an existing BTF rendering approach and the modified material data to simulate the painted appearance of the BTF materials. Our experiments show that the proposed approach can simulate the painted appearance of a material while preserving the characteristic appearance of the original BTF. Our approach is mainly suitable for less specular BTF materials that allow depth reconstruction.
Texture adaptation for progressive meshes
(2006)
Chen, Chih-Chun
;
Chuang, Jung-Hong
;
資訊工程學系
;
Department of Computer Science
Level-of-detail modeling is a vital representation for real-time applications. To support texture mapping progressive meshes (PM), we usually allow the whole PM sequence to share a common texture map. Although such a common texture map can be derived by using appropriate mesh parameterizations that consider the minimization of geometry stretch, texture stretch, or even the texture deviation introduced by edge collapses, we have found that even with a well parameterized texture map, the texture mapped PM still reveals apparent texture distortion due to geometry changes and the nature of linear interpolation used by texture mapping hardware. In this paper we propose a novel, simple, and efficient approach that adapts texture content for each edge collapse, aiming to eliminate texture distortion. A texture adaptation and its inverse are local and incremental operations that can be fully supported by texture mapping hardware, the render-to-texture feature, and the fragment shader Once the necessary correspondence in the partition of texture space is built during the course of PM construction, the texture adaptation or its inverse can be applied on the fly before rendering the simplified or refined model with texture map. We also propose the mechanism of indexing mapping to reduce blurred artifacts due to under-sampling that might be introduced by texture adaptation.