I-Chao Shen

jdilyshen@gmail.com / ichao.shen@ui.is.s.u-tokyo.ac.jp

I am a JSPS gaitoku postdoctoral researcher at The University of Tokyo, working with Takeo Igarashi. My research focus on human-guided optimization, where I explore combinations between different human priors and numerical optimization and develop supportive system for visual content design. I did my Ph.D. in the computer graphics group at CMLab, National Taiwan University, advised by Bing-Yu Chen. I got my B.S. and M.S. degree in Information Management, both from National Taiwan University. During my M.S. period, I worked in the computer graphics group of CMLab with Bing-Yu Chen and Yung-Yu Chuang. After that, I have been a research assistant at the Multimedia Computing Lab with Wen-Huang Cheng, and Imager Lab with Alla Sheffer. Also, I have been a visiting researcher at the Igarashi Lab at the University of Tokyo with Takeo Igarashi.
C.V. | Google Scholar |

Publication

Multi-Resolution Shared Representative Filtering for Real-Time Depth Completion [Coming soon]

Yu-Ting Wu, Tzu-Mao Li, I-Chao Shen, Hong-Shiang Lin, Yung-Yu Chuang
accepted to High-Performance Graphics (HPG) 2021
a real-time depth completion algorithm which can effectively handle large missing regions of depth maps
[project page] [paper]

ClipGen: A Deep Generative Model for Clipart Vectorization and Synthesis

I-Chao Shen, Bing-Yu Chen
accepted to Transaction on Visualization and Computer Graphics (TVCG), 2021
a novel deep learning-based approach for automatically vectorizing and synthesizing the clipart of man-made objects
[project page] [paper] [arxiv]

ClipFlip : Multi-view Clipart Design

I-Chao Shen, Kuan-Hung Liu, Li-Wen Su, Yu-Ting Wu, Bing-Yu Chen
Computer Graphics Forum, Volume 40, Issue 1, Feb 2021
an assistive system for clipart design by providing visual scaffolds from the unseen viewpoints
[project page] [paper] [supplemental material] [arxiv]

Interactive Optimization of Generative Image Modeling using Sequential Subspace Search and Content-based Guidance

Toby Chong Long Hin^*, I-Chao Shen^*, Issei Sato, Takeo Igarashi (*: joint first authors)
Computer Graphics Forum, Volume 40, Issue 1, Feb 2021
a human-in-the-optimization method that allows users to directly explore and search the latent vector space of generative image modeling
[project page] [paper] [arxiv]

ZomeFab: Cost-effective Hybrid Fabrication with Interior Zometool Structure

I-Chao Shen, Ming-Shiuan Chen, Chun-Kai Huang, Bing-Yu Chen
Computer Graphics Forum, Volume 39, Issue 1, Feb 2020
a hybrid 3D fabrication method that combines 3D printing and the Zometool construction set to achieve compact fabrication
[project page] [paper] [arxiv]

Transferring Deep Reinforcement Learning with Adversarial Objective and Augmentation

I-Chao Shen, Shu-Hsuan Hsu, Bing-Yu Chen
to appear in IJCAI-PRICAI 2020 Workshop on Knowledge Based Reinforcement Learning (KBRL)
a semi-supervised transfer learning method for deep reinforcement learning
[paper][arXiv] [present video]

Director-360: Introducing Camera Handling to 360 Cameras

Hao-Juan Huang, I-Chao Shen, Liwei Chan
in proceeding of MobileHCI 2020
[paper]

Perception-Driven Semi-Structured Boundary Vectorization

Shayan Hoshyari, Edoardo A. Dominici, Alla Sheffer, Nathan Carr, Duygu Ceylan,
Zhaowen Wang, I-Chao Shen
ACM Transaction on Graphics (Proceedings of SIGGRAPH 2018)
a boundary vectorization approach leverages human perception of shapes to generate vector images consistent with viewer expectations
[Project Page] [Paper] [Bib]

High-resolution 360 Video Foveated Stitching for Real-time VR

Wei-Tse Lee*, Hsin-I Chen*, Ming-Shiuan Chen, I-Chao Shen, Bing-Yu Chen (*: joint first authors)
Computer Graphics Forum (Proceedings of Pacific Graphics 2017)
a real-time 360◦ video foveatedstitching framework
[Paper] [Slide] [Bib]

A Scalable Active Framework for Region Annotation in 3D Shape Collections

Li Yi, Vladimir G. Kim, Duygu Ceylan, I-Chao Shen, Mengyan Yan, Hao Su, Cewu Lu, Qixing Huang, Alla Sheffer, Leonidas Guibas
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2016)
a novel active learning method capable of enriching massive geometric datasets with accurate semantic region annotations
[Project page] [Paper] [Supplemental] [Bib]

Retargeting 3D Objects and Scenes with a General Framework

Chun-Kai Huang, Yi-Ling Chen, I-Chao Shen, Bing-Yu Chen
Computer Graphics Forum (Proceedings of Pacific Graphics 2016)
an interactive method suitable for retargeting both 3D objects and scenes
[Project page] [Paper] [Supplemental] [Slide] [Bib]

Data-driven Handwriting Synthesis in a Conjoined Manner

Hsin-Yi Chen, Tse-Ju Lin, I-Chao Shen, Bing-Yu Chen
Computer Graphics Forum (Proceedings of Pacific Graphics 2015)
a novel method for synthesizing handwritten text according to the writer’s style while considering characters’ conjoined property
[Project page] [Paper] [Slide] [Bib]

Gestalt Rule Feature Points

I-Chao Shen, Wen-Huang Cheng
IEEE Transactions on Multimedia (TMM), volume 17, number 4, page 526-537, April 2015.
a new approach for detecting reliable visual features from images in different visual styles (e.g., a photo and a painting)
[Paper] [Digital Library] [Bib]

Geometrically Consistent Stereoscopic Image Editing using Patch-based Synthesis

Sheng-Jie Luo, Ying-Tse Sun, I-Chao Shen, Bing-Yu Chen, Yung-Yu Chuang,
IEEE Transactions on Visualization and Computer Graphics (TVCG), Vol.21, No. 1, pp. 56-67, January 2015.
a patch-based synthesis framework for stereoscopic image editing problems, including depth-guided texture synthesis, stereoscopic NPR, paint by depth, content adaptation, and 2D to 3D conversion
[Project Page] [Paper] [Digital Library] [Bib]

Stroke-guided Image Synthesis for Skeletal Structure Editing

Sheng-Jie Luo, Chin-Yu Lin, I-Chao Shen, Bing-Yu Chen,
Computer Graphics Forum (Pacific Graphics 2013)
a technique for synthesizing image objects with different skeletal structures while respecting to an input image object
[Project Page] [Paper] [Slide] [Digital Library] [Bib]

Perspective-Aware Warping for Seamless Stereoscopic Image Cloning

Sheng-Jie Luo, I-Chao Shen, Bing-Yu Chen, Wen-Huang Cheng, Yung-Yu Chuang,
SIGGRAPH ASIA 2012
a novel technique for seamless stereoscopic image cloning, which performs both shape adjustment and color blending
[Project Page] [Paper] [Digital Library] [Bib]

User-Assisted Disparity Maps

Hsin-Yi Chen, Yi-Shan Lin, I-Chao Shen, Sheng-Jie Luo, Wen-Huang Cheng, Bing-Yu Chen,
Pacific Graphics 2012 Short Paper
an intuitive and efficient system for correcting the artifacts and noises caused by imperfect disparity estimation
[Project Page] [Paper] [Bib]

Misc

Texturing and Deforming Meshes with Casual Images

I-Chao Shen, Yi-Hau Wang, Yu-Mei Chen, Bing-Yu Chen
[arXiv]

Data-driven Sketch Beautification with Neural Feature Representation

I-Chao Shen