PG2018 Short Papers and Posters

Permanent URI for this collection

Pacific Graphics 2018 - Short Papers and Posters Proceedings
Hong Kong, China
8-11 October, 2018
(for Full Papers (CGF) see PG 2018 - CGF 37-7)
Registration and Reconstruction
StretchDenoise: Parametric Curve Reconstruction with Guarantees by Separating Connectivity from Residual Uncertainty of Samples
Stefan Ohrhallinger and Michael Wimmer
Lighting and Ray Tracing
Spherical Blue Noise
Kin-Ming Wong and Tien-Tsin Wong
Animation
Robust and Efficient SPH Simulation for High-speed Fluids with the Dynamic Particle Partitioning Method
Zhong Zheng, Yang Gao, Shuai Li, Hong Qin, and Aimin Hao
Sketch-based Interfaces
Bottom-up/Top-down Geometric Object Reconstruction with CNN Classification for Mobile Education
Ting Guo, Rundong Cui, Xiaoran Qin, Yongtao Wang, and Zhi Tang
Appearance and Illumination
Effects of Surface Anisotropy on Perception of Car Body Attractiveness
Jiri Filip and Martina Kolafová
Efficient Metropolis Path Sampling for Material Editing and Re-rendering
Tomoya Yamaguchi, Tatsuya Yatagawa, and Shigeo Morishima
Parameterization and Surface Texture
Mesh Parameterization: a Viewpoint from Constant Mean Curvature Surfaces
Hui Zhao, Kehua Su, Chenchen Li, Boyu Zhang, Shirao Liu, Lei Yang, Na Lei, Steven J. Gortler, and Xianfeng Gu
Tabby: Explorable Design for 3D Printing Textures
Ryo Suzuki, Koji Yatani, Mark D. Gross, and Tom Yeh
Towards Better Quality of Images/Videos
InspireMePosing: Learn Pose and Composition from Portrait Examples
Bin Sheng, Yuxi Jin, Ping Li, Wenxiao Wang, Hongbo Fu, and Enhua Wu
Skeleton and Deformation
Skeleton-based Generalized Cylinder Deformation under the Relative Curvature Condition
Ruibin Ma, Qingyu Zhao, Rui Wang, James Damon, Julian Rosenman, and Stephen Pizer
Anisotropic Spectral Manifold Wavelet Descriptor for Deformable Shape Analysis and Matching
Qinsong Li, Shengjun Liu, Ling Hu, and Xinru Liu
3D Modeling
Recovering 3D Indoor Floor Plans by Exploiting Low-cost Spherical Photography
Giovanni Pintore, Fabio Ganovelli, Ruggero Pintus, Roberto Scopigno, and Enrico Gobbetti
Modeling Detailed Cloud Scene from Multi-source Images
Yunchi Cen, Xiaohui Liang, Junping Chen, Bailin Yang, and Frederick W. B. Li
3D VAE-Attention Network: A Parallel System for Single-view 3D Reconstruction
Fei Hu, Xinyan Yang, Wei Zhong, Long Ye, and Qin Zhang
Progressive 3D Scene Understanding with Stacked Neural Networks
Youcheng Song and Zhengxing Sun
Visualization and GPU
A Visual Analytics Approach for Traffic Flow Prediction Ensembles
Kezhi Kong, Yuxin Ma, Chentao Ye, Junhua Lu, Xiqun Chen, Wei Zhang, and Wei Chen
Robust Material Graphs for Volume Rendering
Ojaswa Sharma, Tushar Arora, and Apoorv Khattar
Light-Field DVR on GPU for Streaming Time-Varying Data
David Ganter, Martin Alain, David Hardman, Aljosa Smolic, and Michael Manzke
Subdivision Surfaces
Gauss-Seidel Progressive Iterative Approximation (GS-PIA) for Loop Surface Interpolation
Zhihao Wang, Yajuan Li, Weiyin Ma, and Chongyang Deng
Direct Limit Volumes: Constant-Time Limit Evaluation for Catmull-Clark Solids
Christian Altenhofen, Joel Müller, Daniel Weber, André Stork, and Dieter W. Fellner
Visual Content Matching and Retrieval
Extreme Feature Regions for Image Matching
Baijiang Fan, Yunbo Rao, Jiansu Pu, and Jianhua Deng
A Deep Learned Method for Video Indexing and Retrieval
Xin Men, Feng Zhou, and Xiaoyong Li
Posters
GPU-based Real-time Cloth Simulation for Virtual Try-on
Tongkui Su, Yan Zhang, Yu Zhou, Yao Yu, and Sidan Du
TAVE: Template-based Augmentation of Visual Effects to Human Actions in Videos
Jingyuan Liu, Xuren Zhou, Hongbo Fu, and Chiew-Lan Tai
Japanese Kanji Font Style Transfer based on GAN with Unpaired Training
Hiroki Sakai, Daisuke Niino, and Takashi Ijiri
Facial-Expression-Aware Emotional Color Transfer Based On Convolutional Neural Network
Min Pei, Shiguang Liu, and Xiaoli Zhang
Shape Interpolation via Multiple Curves
Yusuf Sahillioglu and Melike Aydinlilar

BibTeX (PG2018 Short Papers and Posters)
@inproceedings{
10.2312:pg.20181288,
booktitle = {
Pacific Graphics Posters},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
GPU-based Real-time Cloth Simulation for Virtual Try-on}},
author = {
Su, Tongkui
 and
Zhang, Yan
 and
Zhou, Yu
 and
Yu, Yao
 and
Du, Sidan
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-074-1},
DOI = {
10.2312/pg.20181288}
}
@inproceedings{
10.2312:pg.20181266,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
StretchDenoise: Parametric Curve Reconstruction with Guarantees by Separating Connectivity from Residual Uncertainty of Samples}},
author = {
Ohrhallinger, Stefan
 and
Wimmer, Michael
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181266}
}
@inproceedings{
10.2312:pg.20181289,
booktitle = {
Pacific Graphics Posters},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
TAVE: Template-based Augmentation of Visual Effects to Human Actions in Videos}},
author = {
Liu, Jingyuan
 and
Zhou, Xuren
 and
Fu, Hongbo
 and
Tai, Chiew-Lan
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-074-1},
DOI = {
10.2312/pg.20181289}
}
@inproceedings{
10.2312:pg.20181290,
booktitle = {
Pacific Graphics Posters},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Japanese Kanji Font Style Transfer based on GAN with Unpaired Training}},
author = {
Sakai, Hiroki
 and
Niino, Daisuke
 and
Ijiri, Takashi
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-074-1},
DOI = {
10.2312/pg.20181290}
}
@inproceedings{
10.2312:pg.20181267,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Spherical Blue Noise}},
author = {
Wong, Kin-Ming
 and
Wong, Tien-Tsin
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181267}
}
@inproceedings{
10.2312:pg.20181291,
booktitle = {
Pacific Graphics Posters},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Facial-Expression-Aware Emotional Color Transfer Based On Convolutional Neural Network}},
author = {
Pei, Min
 and
Liu, Shiguang
 and
Zhang, Xiaoli
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-074-1},
DOI = {
10.2312/pg.20181291}
}
@inproceedings{
10.2312:pg.20181292,
booktitle = {
Pacific Graphics Posters},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Shape Interpolation via Multiple Curves}},
author = {
Sahillioglu, Yusuf
 and
Aydinlilar, Melike
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-074-1},
DOI = {
10.2312/pg.20181292}
}
@inproceedings{
10.2312:pg.20181268,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Robust and Efficient SPH Simulation for High-speed Fluids with the Dynamic Particle Partitioning Method}},
author = {
Zheng, Zhong
 and
Gao, Yang
 and
Li, Shuai
 and
Qin, Hong
 and
Hao, Aimin
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181268}
}
@inproceedings{
10.2312:pg.20181269,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Bottom-up/Top-down Geometric Object Reconstruction with CNN Classification for Mobile Education}},
author = {
Guo, Ting
 and
Cui, Rundong
 and
Qin, Xiaoran
 and
Wang, Yongtao
 and
Tang, Zhi
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181269}
}
@inproceedings{
10.2312:pg.20181270,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Effects of Surface Anisotropy on Perception of Car Body Attractiveness}},
author = {
Filip, Jiri
 and
Kolafová, Martina
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181270}
}
@inproceedings{
10.2312:pg.20181271,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Efficient Metropolis Path Sampling for Material Editing and Re-rendering}},
author = {
Yamaguchi, Tomoya
 and
Yatagawa, Tatsuya
 and
Morishima, Shigeo
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181271}
}
@inproceedings{
10.2312:pg.20181272,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Mesh Parameterization: a Viewpoint from Constant Mean Curvature Surfaces}},
author = {
Zhao, Hui
 and
Su, Kehua
 and
Li, Chenchen
 and
Zhang, Boyu
 and
Liu, Shirao
 and
Yang, Lei
 and
Lei, Na
 and
Gortler, Steven J.
 and
Gu, Xianfeng
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181272}
}
@inproceedings{
10.2312:pg.20181273,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Tabby: Explorable Design for 3D Printing Textures}},
author = {
Suzuki, Ryo
 and
Yatani, Koji
 and
Gross, Mark D.
 and
Yeh, Tom
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181273}
}
@inproceedings{
10.2312:pg.20181274,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
InspireMePosing: Learn Pose and Composition from Portrait Examples}},
author = {
Sheng, Bin
 and
Jin, Yuxi
 and
Li, Ping
 and
Wang, Wenxiao
 and
Fu, Hongbo
 and
Wu, Enhua
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181274}
}
@inproceedings{
10.2312:pg.20181275,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Skeleton-based Generalized Cylinder Deformation under the Relative Curvature Condition}},
author = {
Ma, Ruibin
 and
Zhao, Qingyu
 and
Wang, Rui
 and
Damon, James
 and
Rosenman, Julian
 and
Pizer, Stephen
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181275}
}
@inproceedings{
10.2312:pg.20181276,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Anisotropic Spectral Manifold Wavelet Descriptor for Deformable Shape Analysis and Matching}},
author = {
Li, Qinsong
 and
Liu, Shengjun
 and
Hu, Ling
 and
Liu, Xinru
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181276}
}
@inproceedings{
10.2312:pg.20181277,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Recovering 3D Indoor Floor Plans by Exploiting Low-cost Spherical Photography}},
author = {
Pintore, Giovanni
 and
Ganovelli, Fabio
 and
Pintus, Ruggero
 and
Scopigno, Roberto
 and
Gobbetti, Enrico
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181277}
}
@inproceedings{
10.2312:pg.20181278,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Modeling Detailed Cloud Scene from Multi-source Images}},
author = {
Cen, Yunchi
 and
Liang, Xiaohui
 and
Chen, Junping
 and
Yang, Bailin
 and
Li, Frederick W. B.
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181278}
}
@inproceedings{
10.2312:pg.20181279,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
3D VAE-Attention Network: A Parallel System for Single-view 3D Reconstruction}},
author = {
Hu, Fei
 and
Yang, Xinyan
 and
Zhong, Wei
 and
Ye, Long
 and
Zhang, Qin
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181279}
}
@inproceedings{
10.2312:pg.20181280,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Progressive 3D Scene Understanding with Stacked Neural Networks}},
author = {
Song, Youcheng
 and
Sun, Zhengxing
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181280}
}
@inproceedings{
10.2312:pg.20181281,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
A Visual Analytics Approach for Traffic Flow Prediction Ensembles}},
author = {
Kong, Kezhi
 and
Ma, Yuxin
 and
Ye, Chentao
 and
Lu, Junhua
 and
Chen, Xiqun
 and
Zhang, Wei
 and
Chen, Wei
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181281}
}
@inproceedings{
10.2312:pg.20181282,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Robust Material Graphs for Volume Rendering}},
author = {
Sharma, Ojaswa
 and
Arora, Tushar
 and
Khattar, Apoorv
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181282}
}
@inproceedings{
10.2312:pg.20181284,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Gauss-Seidel Progressive Iterative Approximation (GS-PIA) for Loop Surface Interpolation}},
author = {
Wang, Zhihao
 and
Li, Yajuan
 and
Ma, Weiyin
 and
Deng, Chongyang
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181284}
}
@inproceedings{
10.2312:pg.20181283,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Light-Field DVR on GPU for Streaming Time-Varying Data}},
author = {
Ganter, David
 and
Alain, Martin
 and
Hardman, David
 and
Smolic, Aljosa
 and
Manzke, Michael
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181283}
}
@inproceedings{
10.2312:pg.20181285,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Direct Limit Volumes: Constant-Time Limit Evaluation for Catmull-Clark Solids}},
author = {
Altenhofen, Christian
 and
Müller, Joel
 and
Weber, Daniel
 and
Stork, André
 and
Fellner, Dieter W.
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181285}
}
@inproceedings{
10.2312:pg.20181287,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
A Deep Learned Method for Video Indexing and Retrieval}},
author = {
Men, Xin
 and
Zhou, Feng
 and
Li, Xiaoyong
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181287}
}
@inproceedings{
10.2312:pg.20181286,
booktitle = {
Pacific Graphics Short Papers},
editor = {
Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
}, title = {{
Extreme Feature Regions for Image Matching}},
author = {
Fan, Baijiang
 and
Rao, Yunbo
 and
Pu, Jiansu
 and
Deng, Jianhua
}, year = {
2018},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-073-4},
DOI = {
10.2312/pg.20181286}
}

Browse

Recent Submissions

Now showing 1 - 28 of 28
  • Item
    Frontmatter: Pacific Graphics 2018 - Short Papers and Posters
    (The Eurographics Association, 2018) Fu, Hongbo; Ghosh, Abhijeet; Kopf, Johannes; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
  • Item
    GPU-based Real-time Cloth Simulation for Virtual Try-on
    (The Eurographics Association, 2018) Su, Tongkui; Zhang, Yan; Zhou, Yu; Yu, Yao; Du, Sidan; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    We present a novel real-time approach for dynamic detailed clothing simulation on a moving body. The most distinctive feature of our method is that it divides dynamic simulation into two parts: local driving and static cloth simulation. In local driving, feature points of clothing will be handled between two consecutive frames. And then we apply static cloth simulation for a specific frame. Both parts are ecxuted in an entire parallel way. In practice, our system achieves real-time virtual try-on using a depth camera to capture the moving body model and meanwhile, keeps high-fidelity. Experimental results indicate that our method has significant speedups over prior related techniques.
  • Item
    StretchDenoise: Parametric Curve Reconstruction with Guarantees by Separating Connectivity from Residual Uncertainty of Samples
    (The Eurographics Association, 2018) Ohrhallinger, Stefan; Wimmer, Michael; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    We reconstruct a closed denoised curve from an unstructured and highly noisy 2D point cloud. Our proposed method uses a two-pass approach: Previously recovered manifold connectivity is used for ordering noisy samples along this manifold and express these as residuals in order to enable parametric denoising. This separates recovering low-frequency features from denoising high frequencies, which avoids over-smoothing. The noise probability density functions (PDFs) at samples are either taken from sensor noise models or from estimates of the connectivity recovered in the first pass. The output curve balances the signed distances (inside/outside) to the samples. Additionally, the angles between edges of the polygon representing the connectivity become minimized in the least-square sense. The movement of the polygon's vertices is restricted to their noise extent, i.e., a cut-off distance corresponding to a maximum variance of the PDFs. We approximate the resulting optimization model, which consists of higher-order functions, by a linear model with good correspondence. Our algorithm is parameter-free and operates fast on the local neighborhoods determined by the connectivity. This enables us to guarantee stochastic error bounds for sampled curves corrupted by noise, e.g., silhouettes from sensed data, and we improve on the reconstruction error from ground truth. Source code is available online. An extended version is available at: https://arxiv.org/abs/1808.07778
  • Item
    TAVE: Template-based Augmentation of Visual Effects to Human Actions in Videos
    (The Eurographics Association, 2018) Liu, Jingyuan; Zhou, Xuren; Fu, Hongbo; Tai, Chiew-Lan; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    We present TAVE, a framework that allows novice users to add interesting visual effects by mimicking human actions in a given template video, in which pre-defined visual effects have already been associated with specific human actions. Our framework is mainly based on high-level features of human pose extracted from video frames, and uses low-level image features as the auxiliary information. We encode an action into a set of code sequences representing joint motion directions and use a finite state machine to recognize the action state of interest. The visual effects, possibly with occlusion masks, can be automatically transferred from the template video to a target video containing similar human actions.
  • Item
    Japanese Kanji Font Style Transfer based on GAN with Unpaired Training
    (The Eurographics Association, 2018) Sakai, Hiroki; Niino, Daisuke; Ijiri, Takashi; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    To design a whole package of Japanese font is labor consuming, since it usually contains about 30k kanji characters. To support an efficient design process, this poster attempts to adopt a style transfer algorithm for font package completion. Given two font packages where one contains all characters and the other lacks a large part, we train CycleGAN to perform style transfer between the two packages and transfer the style from the former to the latter. To illustrate the feasibility of our technique, we performed style transfer experiments and achieved visually plausible results by using a relatively small training data set.
  • Item
    Spherical Blue Noise
    (The Eurographics Association, 2018) Wong, Kin-Ming; Wong, Tien-Tsin; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    We present a physically based method which generates unstructured uniform point set directly on the S2-sphere. Spherical uniform point sets are useful for illumination sampling in Quasi Monte Carlo (QMC) rendering but it is challenging to generate high quality uniform point sets directly. Most methods rely on mapping the low discrepancy unit square point sets to the spherical domain. However, these transformed point sets often exhibit sub-optimal uniformity due to the inability of preserving the low discrepancy properties. Our method is designed specifically for direct generation of uniform point sets in the spherical domain. We name our generated result as Spherical Blue Noise point set because it shares similar point distribution characteristics with the 2D blue noise. Our point sets possess high spatial uniformity without a global structure, and we show that they deliver competitive results for illumination integration in QMC rendering, and general numerical integration on the spherical domain.
  • Item
    Facial-Expression-Aware Emotional Color Transfer Based On Convolutional Neural Network
    (The Eurographics Association, 2018) Pei, Min; Liu, Shiguang; Zhang, Xiaoli; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    Emotional color transfer aims to change the evoked emotion of the source image to that of the target image by adjusting color distribution. Most of existing emotional color transfer methods ignore the facial expression features in the image. Therefore, we propose a new facial-expression-aware emotional color transfer framework. We firstly predict the emotion label of the image through the emotion classification network. Then, emotion labels are matched with pre-trained emotional models. Finally, we use the matched emotion model to transfer the color of the target image to the input image. Experiments demonstrate that our method outperforms the state-of-the-arts, which can successfully capture and transfer sophisticated emotion features.
  • Item
    Shape Interpolation via Multiple Curves
    (The Eurographics Association, 2018) Sahillioglu, Yusuf; Aydinlilar, Melike; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    We present a method that interpolates new shapes between a given pair of source and target shapes. To this end, we utilize a database of related shapes that is used to replace the direct transition from the source to the target by a composition of small transitions. This so-called data-driven interpolation scheme proved useful as long as the database is sufficiently large. We advance this idea one step further by processing the database shapes part by part, which in turn enables realistic interpolations with relatively small databases. We obtain promising preliminary results and point out potential improvements that we intend to address in our future work.
  • Item
    Robust and Efficient SPH Simulation for High-speed Fluids with the Dynamic Particle Partitioning Method
    (The Eurographics Association, 2018) Zheng, Zhong; Gao, Yang; Li, Shuai; Qin, Hong; Hao, Aimin; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    In this paper, our research efforts are devoted to the efficiency issue of the SPH simulation when the ratio of velocities among fluid particles is large. Specifically, we introduce a k-means clustering method into the SPH framework to dynamically partition fluid particles into two disjoint groups based on their velocities, we then use a two-scale time step scheme for these two types of particles. The smaller time steps are for particles with higher speed in order to preserve temporal details and guarantee the numerical stability. In contrast, the larger time steps are used for particles with smaller speeds to reduce the computational expense, and both types of particles are tightly coupled in the simulation.We conduct various experiments which have manifested the advantages of our methods over the conventional SPH technique and its new variants in terms of efficiency and stability.
  • Item
    Bottom-up/Top-down Geometric Object Reconstruction with CNN Classification for Mobile Education
    (The Eurographics Association, 2018) Guo, Ting; Cui, Rundong; Qin, Xiaoran; Wang, Yongtao; Tang, Zhi; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    Geometric objects in educational materials are often illustrated as 2D line drawings, which results in the loss of depth information. To alleviate the problem of fully understanding the 3D structure of geometric objects, we propose a novel method to reconstruct the 3D shape of a geometric object illustrated in a line drawing image. In contrast to most existing methods, ours directly take a single line drawing image as input and generate a valid sketch for reconstruction. Given a single input line drawing image, we first classify the geometric object in the image with convolution neural network (CNN). More specifically, we pre-train the model with simulated images to alleviate the problems of data collection and unbalanced distribution among different classes. Then, we generate the sketch of the geometric object with our proposed bottom-up and top-down scheme. Finally, we finish reconstruction by minimizing an objective function of reconstruction error. Extensive experimental results demonstrate that our method performs significantly better in both accuracy and efficiency compared with the existing methods.
  • Item
    Effects of Surface Anisotropy on Perception of Car Body Attractiveness
    (The Eurographics Association, 2018) Filip, Jiri; Kolafová, Martina; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    In the automotive industry effect coatings are used to introduce customized product design, visually communicating the unique impression of a car. Industrial effect coatings systems achieve primarily a globally isotropic appearance, i.e., surface appearance that does not change when material rotates around its normal. To the contrary, anisotropic appearance exhibits variable behavior due to oriented structural elements. This paper studies to what extent anisotropic appearance improves a visual impression of a car body beyond a standard isotropic one. We ran several psychophysical studies identifying the proper alignment of an anisotropic axis over a car body, showing that regardless of the illumination conditions, subjects always preferred an anisotropy axis orthogonal to car body orientation. The majority of subjects also found the anisotropic appearance more visually appealing than the isotropic one.
  • Item
    Efficient Metropolis Path Sampling for Material Editing and Re-rendering
    (The Eurographics Association, 2018) Yamaguchi, Tomoya; Yatagawa, Tatsuya; Morishima, Shigeo; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    This paper proposes efficient path sampling for re-rendering scenes after material editing. The proposed sampling method is based on Metropolis light transport (MLT) and distributes more path samples to pixels whose values have been changed significantly by editing. First, we calculate the difference between images before and after editing to estimate the changes in pixel values. In this step, we render the difference image directly rather than calculating the difference in the images by separately rendering the images before and after editing. Then, we sample more paths for pixels with larger difference values and render the scene after editing by reducing variances of Monte Carlo estimators using the control variates. Thus, we can obtain rendering results with a small amount of noise using only a small number of path samples. We examine the proposed sampling method with a range of scenes and demonstrate that it achieves lower estimation errors and variances over the state-of-the-art methods.
  • Item
    Mesh Parameterization: a Viewpoint from Constant Mean Curvature Surfaces
    (The Eurographics Association, 2018) Zhao, Hui; Su, Kehua; Li, Chenchen; Zhang, Boyu; Liu, Shirao; Yang, Lei; Lei, Na; Gortler, Steven J.; Gu, Xianfeng; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    We present a unified mesh paramterization algorithm for both planar and spheric domains based on mesh deformation. Unlike previous methods, our approach can produce intermediate frames from the original to target meshes. We derive and define a novel geometric flow: unit normal flow(UNF) and prove that if unit normal flow converges, it will deform a surface to a constant mean curvature(CMC) surface, such as plane and sphere. Our method works by deforming meshes of disk topology to planes, meshes of spheric topology to spheres. The unit normal flow we propose also suggests a potential direction for creating CMC surfaces.
  • Item
    Tabby: Explorable Design for 3D Printing Textures
    (The Eurographics Association, 2018) Suzuki, Ryo; Yatani, Koji; Gross, Mark D.; Yeh, Tom; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    This paper presents Tabby, an interactive and explorable design tool for 3D printing textures. Tabby allows texture design with direct manipulation in the following workflow: 1) select a target surface, 2) sketch and manipulate a texture with 2D drawings, and then 3) generate 3D printing textures onto an arbitrary curved surface. To enable efficient texture creation, Tabby leverages an auto-completion approach which automates the tedious, repetitive process of applying texture, while allowing flexible customization. Our user evaluation study with seven participants confirms that Tabby can effectively support the design exploration of different patterns for both novice and experienced users.
  • Item
    InspireMePosing: Learn Pose and Composition from Portrait Examples
    (The Eurographics Association, 2018) Sheng, Bin; Jin, Yuxi; Li, Ping; Wang, Wenxiao; Fu, Hongbo; Wu, Enhua; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    Since people tend to build relationship with others by personal photography, capturing high quality photographs on mobile device has become a strong demand. We propose a portrait photography guidance system to guide user's photographing. We consider current scene image as our input and find professional photograph examples with similar aesthetic features for it. Deep residual network is introduced to gather scene classification information and represent common photograph rules by features, and random forest is adopted to establishing mapping relations between extracted features and examples. Besides, we implement our guidance system on a camera application and evaluate it by user study.
  • Item
    Skeleton-based Generalized Cylinder Deformation under the Relative Curvature Condition
    (The Eurographics Association, 2018) Ma, Ruibin; Zhao, Qingyu; Wang, Rui; Damon, James; Rosenman, Julian; Pizer, Stephen; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    Deformation of a generalized cylinder with a parameterized shape change of its centerline is a non-trivial task when the surface is represented as a high-resolution triangle mesh, particularly when self-intersection and local distortion are to be avoided. We introduce a deformation approach that satisfies these properties based on the skeleton (densely sampled centerline and cross sections) of a generalized cylinder. Our approach uses the relative curvature condition to extract a reasonable centerline for a generalized cylinder whose orthogonal cross sections will not intersect. Given the desired centerline shape as a parametric curve, the displacements on the cross sections are determined while controlling for twisting effects, and under this constraint a vertex-wise displacement field is calculated by minimizing a quadratic surface bending energy. The method is tested on complicated generalized cylindrical objects. In particular, we discuss one application of the method for human colon (large intestine) visualization.
  • Item
    Anisotropic Spectral Manifold Wavelet Descriptor for Deformable Shape Analysis and Matching
    (The Eurographics Association, 2018) Li, Qinsong; Liu, Shengjun; Hu, Ling; Liu, Xinru; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    In this paper, we present a novel framework termed Anisotropic Spectral Manifold Wavelet Transform (ASMWT) for shape analysis. ASMWT comprehensively analyzes the signals from multiple directions on local manifold regions of the shape with a series of low-pass and band-pass frequency filters in each direction. Using the ASMWT coefficients of a very simple function, we efficiently construct a localizable and discriminative multiscale point descriptor, named as the Anisotropic Spectral Manifold Wavelet Descriptor (ASMWD). Since the filters used in our descriptor are direction-sensitive and able to robustly reconstruct the signals with a finite number of scales, it makes our descriptor be intrinsic-symmetry unambiguous, compact as well as efficient. The extensive experimental results demonstrate that our method achieves significant performance than several state-of-the-art methods when applied in vertex-wise shape matching.
  • Item
    Recovering 3D Indoor Floor Plans by Exploiting Low-cost Spherical Photography
    (The Eurographics Association, 2018) Pintore, Giovanni; Ganovelli, Fabio; Pintus, Ruggero; Scopigno, Roberto; Gobbetti, Enrico; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    We present a novel approach to automatically recover, from a small set of partially overlapping panoramic images, an indoor structure representation in terms of a 3D floor plan registered with a set of 3D environment maps. Our improvements over previous approaches include a new method for geometric context extraction based on a 3D facets representation, which combines color distribution analysis of individual images with sparse multi-view clues, as well as an efficient method to combine the facets from different point-of-view in the same world space, considering the reliability of the facets contribution. The resulting capture and reconstruction pipeline automatically generates 3D multi-room environments where most of the other previous approaches fail, such as in presence of hidden corners, large clutter and sloped ceilings, even without involving additional dense 3D data or tools. We demonstrate the effectiveness and performance of our approach on different real-world indoor scenes.
  • Item
    Modeling Detailed Cloud Scene from Multi-source Images
    (The Eurographics Association, 2018) Cen, Yunchi; Liang, Xiaohui; Chen, Junping; Yang, Bailin; Li, Frederick W. B.; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    Realistic cloud is essential for enhancing the quality of computer graphics applications, such as flight simulation. Data-driven method is an effective way in cloud modeling, but existing methods typically only utilize one data source as input. For example, natural images are usually used to model small-scale cloud with details, and satellite images and WRF data are used to model large scale cloud without details. To construct large-scale cloud scene with details, we propose a novel method to extract relevant cloud information from both satellite and natural images. Experiments show our method can produce more detailed cloud scene comparing with existing methods.
  • Item
    3D VAE-Attention Network: A Parallel System for Single-view 3D Reconstruction
    (The Eurographics Association, 2018) Hu, Fei; Yang, Xinyan; Zhong, Wei; Ye, Long; Zhang, Qin; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    3D object reconstruction from single view image is a challenge task. Due to the fact that the information contained in one isolated image is not sufficient for reasonable 3D shape reconstruction, the existing results on single-view 3D reconstruction always lack marginal voxels. To tackle this problem, we propose a parallel system named 3D VAE-attention network (3VAN) for single view 3D reconstruction. Distinct from the common encoder-decoder structure, the proposed network consists of two parallel branches, 3D-VAE and Attention Network. 3D-VAE completes the general shape reconstruction by an extension of standard VAE model, and Attention Network supplements the missing details by a 3D reconstruction attention network. In the experiments, we verify the feasibility of our 3VAN on the ShapeNet and PASCAL 3D+ datasets. By comparing with the state-of-art methods, the proposed 3VAN can produce more precise 3D object models in terms of both qualitative and quantitative evaluation.
  • Item
    Progressive 3D Scene Understanding with Stacked Neural Networks
    (The Eurographics Association, 2018) Song, Youcheng; Sun, Zhengxing; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    3D scene understanding is difficult due to the natural hierarchical structures and complicated contextual relationships in the 3d scenes. In this paper, a progressive 3D scene understanding method is proposed. The scene understanding task is decomposed into several different but related tasks, and semantic objects are progressively separated from coarse to fine. It is achieved by stacking multiple segmentation networks. The former network segments the 3D scene at a coarser level and passes the result as context to the latter one for a finer-grained segmentation. For the network training, we build a connection graph (vertices indicating objects and edges' weights indicating contact area between objects), and calculate a maximum spanning tree to generate coarse-to-fine labels. Then we train the stacked network by hierarchical supervision based on the generated coarseto- fine labels. Finally, using the trained model, we can not only obtain better segmentation accuracy at the finest-grained than directly using the segmentation network, but also obtain a hierarchical understanding result of the 3d scene as a bonus.
  • Item
    A Visual Analytics Approach for Traffic Flow Prediction Ensembles
    (The Eurographics Association, 2018) Kong, Kezhi; Ma, Yuxin; Ye, Chentao; Lu, Junhua; Chen, Xiqun; Zhang, Wei; Chen, Wei; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    Traffic flow prediction plays a significant role in Intelligent Transportation Systems (ITS). Due to the variety of prediction models, the prediction results form an intricate structure of ensembles and hence leave a challenge of understanding and evaluating the ensembles from different perspectives. In this paper, we propose a novel visual analytics approach for analyzing the predicted ensembles. Our approach models the uncertainty of different traffic flow prediction results. The variations of space, time, and network structures of those results are presented with the visualization designs. The visual interface provides a suite of interactions to enhance exploration of the ensembles. With the system, analysts can discover some intrinsic patterns in the ensemble. We use real-world urban traffic data to demonstrate the effectiveness of our system.
  • Item
    Robust Material Graphs for Volume Rendering
    (The Eurographics Association, 2018) Sharma, Ojaswa; Arora, Tushar; Khattar, Apoorv; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    A good transfer function in volume rendering requires careful consideration of the materials present in a volume. In this work we propose a graph based method that considerably reduces manual effort required in designing a transfer function and provides an easy interface for interaction with the volume. Our novel contribution is in proposing an algorithm for robust deduction of a material graph from a set of disconnected edges. Since we compute material topology of the objects, an enhanced rendering is possible with our method. This also allows us to selectively render objects and depict adjacent materials in a volume.
  • Item
    Gauss-Seidel Progressive Iterative Approximation (GS-PIA) for Loop Surface Interpolation
    (The Eurographics Association, 2018) Wang, Zhihao; Li, Yajuan; Ma, Weiyin; Deng, Chongyang; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    We propose a Gauss-Seidel progressive iterative approximation (GS-PIA) method for Loop subdivision surface interpolation by combining classical Gauss-Seidel iterative method for linear system and progressive iterative approximation (PIA) for data interpolation. We prove that GS-PIA is convergent by applying matrix theory. GS-PIA algorithm retains the good features of the classical PIA method, such as the resemblance with the given mesh and the advantages of both a local method and a global method. Compared with some existed interpolation methods of subdivision surfaces, GS-PIA algorithm has advantages in three aspects. First, it has a faster convergence rate compared with the PIA and WPIA algorithms. Second, compared with WPIA algorithm, GS-PIA algorithm need not to choose weights. Third, GS-PIA need not to modify the mesh topology compared with other methods with fairness measures. Numerical examples for Loop subdivision surfaces interpolation illustrated in this paper show the efficiency and effectiveness of GS-PIA algorithm.
  • Item
    Light-Field DVR on GPU for Streaming Time-Varying Data
    (The Eurographics Association, 2018) Ganter, David; Alain, Martin; Hardman, David; Smolic, Aljosa; Manzke, Michael; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    Direct Volume Rendering (DVR) of volume data can be a memory intensive task in terms of footprint and cache-coherency. Rayguided methods may not be the best option to interactively render to light-fields due to feedback loops and sporadic sampling, and pre-computation can rule out time-varying data. We present a pipelined approach to schedule the rendering of sub-regions of streaming time-varying volume data while minimising intermediate sub-buffers needed, sharing the work load between CPU and GPU. We show there is significant advantage to using such an approach.
  • Item
    Direct Limit Volumes: Constant-Time Limit Evaluation for Catmull-Clark Solids
    (The Eurographics Association, 2018) Altenhofen, Christian; Müller, Joel; Weber, Daniel; Stork, André; Fellner, Dieter W.; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    We present a novel approach for efficient limit volume evaluation on Catmull-Clark (CC) subdivision solids. Although several analogies exist between subdivision surfaces and subdivision volumes, extending Stam's limit evaluation technique from 2 to 3 dimensions is not straightforward, as irregularities and boundaries introduce new challenges in the volumetric case. We present new direct evaluation techniques for irregular volumetric topologies and boundary cells, which allow for calculating the limit of CC subdivision solids at arbitrary parameter values in constant time. Evaluation of limit points is a central aspect when using CC solids for applications such as simulation and multi-material additive manufacturing, or as a compact volumetric representation scheme for continuous scalar fields. We demonstrate that our approach is faster than existing evaluation techniques for every topological configuration or target parameter (u, v, w) that requires more than two local subdivision steps.
  • Item
    A Deep Learned Method for Video Indexing and Retrieval
    (The Eurographics Association, 2018) Men, Xin; Zhou, Feng; Li, Xiaoyong; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    In this paper, we proposed a deep neural network based method for content based video retrieval. Our approach leveraged the deep neural network to generate the semantic information and introduced the graph-based storage structure to establish the video indices. We devised the Inception-Single Shot Multibox Detector (ISSD) and RI3D model to extract spatial semantic information (objects) and extract temporal semantic information (actions). Our ISSD model achieved a mAP of 26.7% on MS COCO dataset, increasing 3.2% over the original SSD model, while the RI3D model achieved a top-1 accuracy of 97.7% on dataset UCF-101. And we also introduced the graph structure to build the video index with the temporal and spatial semantic information. Our experiment results showed that the deep learned semantic information is highly effective for video indexing and retrieval.
  • Item
    Extreme Feature Regions for Image Matching
    (The Eurographics Association, 2018) Fan, Baijiang; Rao, Yunbo; Pu, Jiansu; Deng, Jianhua; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    Extreme feature regions are increasingly critical for many image matching applications on affine image-pairs. In this paper, we focus on the time-consumption and accuracy of using extreme feature regions to do the affine-invariant image matching. Specifically, we proposed novel image matching algorithm using three types of critical points in Morse theory to calculate precise extreme feature regions. Furthermore, Random Sample Consensus (RANSAC) method is used to eliminate the features of complex background, and improve the accuracy of the extreme feature regions. Moreover, the saddle regions is used to calculate the covariance matrix for image matching. Extensive experiments on several benchmark image matching databases validate the superiority of the proposed approaches over many recently proposed affine-invariant SIFT algorithms.