logo

字形计算实验室

连宙辉 副教授、博士生导师

My English Web Site 

1985年5月出生于福建福州。北京大学王选计算机研究所副教授(2015.8~),北京大学计算机科学技术研究所讲师(2013.6~2015.8),北京大学计算机科学技术研究所博士后研究人员(2011.7~2013.6),美国国家标准与技术研究院(NIST)信息技术实验室Guest Researcher(2009.7~2011.7),英国卡迪夫大学计算机学院Academic Visitor(2008.1~2009.1)。博士毕业于北京航空航天大学自动化科学与电气工程学院,本科毕业于南京航空航天大学自动化学院。入选国家级青年人才计划,主持/主持完成包括国家自然科学基金面上资助项目、国家语委重点项目、国家自然科学基金青年科学基金项目等多项国家和省部级科研项目。研究方向为计算机图形学、计算机视觉与人工智能。近年来,在国际重要乃至顶级的期刊(TOG, IJCV, TPAMI等)与会议(SIGGRAPH/SIGGRAPH Asia, CVPR, NeurIPS, IJCAI, AAAI等)上发表论文90多篇。多次担任NeurIPS、ICCV、CVPR、IJCAI、AAAI等国际顶级学术会议的领域主席(AC)或SPC,曾获2023年度北京市技术发明奖二等奖(排名1)、2021年中国专利优秀奖(排名1)、2019年中国人工智能学会吴文俊人工智能优秀青年奖、2019年北京市科技新星计划、CVPR杰出审稿人(2020/2021)、2022年北京大学黄廷方/信和青年杰出学者奖、北京大学第二十一届青年教师教学基本功比赛(理工科类)优秀指导教师奖、北京大学第十四届青年教师教学基本功比赛理工组一等奖等奖励/资助。


代表性论文(*表示通讯作者):

期刊:

[1] G. Pu, Y. Men, Y. Mao, Y. Jiang, W. Ma, Z. Lian*. Controllable Image Synthesis with Attribute-Decomposed GAN. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2023 

[2] Y. Men, Y. Yao, M. Cui, Z. Lian*, X. Xie. DCT-Net: Domain-calibrated Translation for Portrait Stylization. ACM Transactions on Graphics (TOG) (presented at SIGGRAPH 2022)

[3] Y. Wang, Z. Lian*. DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning, ACM Transactions on Graphics (TOG). 40(6): 265, 2021 (presented at SIGGRAPH Asia 2021) 

[4] Y. Wang, Y. Gao, Z. Lian*.  Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning. ACM Transactions on Graphics (TOG).2020  (presented at SIGGRAPH 2020)

[5] Z. Lian*, B. Zhao, X. Chen, J. Xiao. EasyFont: A Style Learning based System to Easily Build Your Large-scale Handwriting Fonts, ACM Transactions on Graphics (TOG), 2019 (presented at Siggraph 2019)

[6] Y. Gao, Y. Guan, Z. Lian*, Y. Tang, J. Xiao.  Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning. ACM Transactions on Graphics (TOG).vol. 38, no. 6, Article No. 185, 2019 (presented at SIGGRAPH Asia 2019)

[7] Z. Lian*, A. Godil, J. Xiao. Feature-preserved 3D Canonical Form, International Journal of computer Vision (IJCV), vol. 102, no. 1-3, pp. 221-238, 2013

[8] Z. Lian*, Y. Gao. CVFont: Synthesizing Chinese Vector Fonts via Deep Layout Inferring,  Computer Graphics Forum (CGF), 2022 (Accepted)

[9] Z. Lian*, A. Godil, B. Bustos, M. Daoudi, J. Hermans, S. Kawamura, Y. Kurita, G. Lavoué, H.V. Nguyen, R. Ohbuchi, Y. Ohkita, Y. Ohishi, F. Porikli, M. Reuter, I. Sipiran, D. Smeets, P. Suetens, H. Tabia, D. Vandermeulen. A Comparison of Methods for Non-rigid 3D Shape Retrieval, Pattern Recognition (PR), vol. 46, no. 1, pp.449-461, 2013 (ESI top 1% highly-cited paper)

[10] Z. Lian*, P.L. Rosin, X. Sun. Rectilinearity of 3D meshes, International Journal of Computer Vision (IJCV), vol. 89, no. 2-3, pp. 130-151, 2010


会议: 

[1] G. Pu, P.-S. Wang, Z. Lian*. SinMPI: Novel View Synthesis from a Single Image with Expanded Multiplane Images. SIGGRAPH Asia 2023 (CCF-A) 

[2] Y. Wang, Y. Wang, L. Yu, Y. Zhu, Z. Lian*. DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality. CVPR 2023 (Accepted) (CCF-A) 

[3] Z. Xia, B. Xiong, Z. Lian*. VecFontSDF: Learning to Reconstruct and Synthesize High-quality Vector Fonts via Signed Distance Functions. CVPR 2023 (accepted) (CCF-A)

[4] Y. Wang, G. Pu, W. Luo, Y. Wang, P. Xiong, H. Kang, Z. Lian*. Aesthetic Text Logo Synthesis via Content-aware Layout Inferring. CVPR 2022 

[5] Y. Men, Y. Yao, M. Cui, Z. Lian, X. Xie, X. Hua. Unpaired Cartoon Image Synthesis via Gated Cycle Mapping. CVPR 2022 

[6] T. Sheng, J. Chen, Z. Lian*. CentripetalText: An Efficient Text Instance Representation for Scene Text Detection, NeurIPS 2021 (accepted)  

[7] Y. Gao, F. Wei, J. Bao, S. Gu, D. Chen, F. Wen, Z. Lian*. High-Fidelity and Arbitrary Face Editing, CVPR 2021 (accepted)

[8] X. Zhang, X. Sun, Z. Lian*. BoW Pooling: A Plug-and-Play Unit for Feature Aggregation of Point Clouds, AAAI 2021

[9] Y. Liu, Z. Lian*. FontRL: Chinese Font Synthesis via Deep Reinforcement Learning, AAAI 2021

[10] Y. Men, Y. Mao, Y. Jiang, W. Ma, Z. Lian*, Controllable Person Image Synthesis with Attribute-Decomposed GAN. CVPR 2020 (oral)

[11] Y. Men, Z. Lian*, Y. Tang, J. Xiao. DynTypo: Example-based Dynamic Text Effects Transfer, CVPR 2019

[12] X. Sun, Z. Lian*, J. Xiao, SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentation,  ACM International Conference on Multimedia (MM), 2019 

[13] Y. Jiang,Z. Lian*, Y. Tang, J. Xiao. SCFont: Structure-guided Chinese Font Generation via Deep Stacked Networks. AAAI 2019

[14] Y. Men, Z. Lian*, Y. Tang, J. Xiao. A Common Framework for Interactive Texture Transfer. CVPR 2018 (Spotlight)

[15] J. Liu, Z. Lian*, Y. Wang, J. Xiao. Incremental Kernel Null Space Discriminant Analysis for Novelty Detection. CVPR 2017  (Data & Source code)

[16] S. Yang, J. Liu, Z. Lian, Z. Guo. Awesome Typography: Statistics-Based Text Effects Transfer. CVPR 2017 

[17] Z. Lian*, B. Zhao, J. Xiao. Automatic Generation of Large-scale Handwriting Fonts via Style Learning. Siggraph Asia 2016, Artical no. 12 (Technical briefs), 2016

[18] R. Sun, Z. Lian*, Y. Tang, J. Xiao. Aesthetic Visual Quality Evaluation of Chinese Handwritings. IJCAI 2015, pp. 2510-2516, 2015 (Data & Source code)

[19] J. Liu, Z. Lian, J. Feng, B. Zhou. Sketch based Modeling via Manifold Regularization. Siggraph Asia 2015, Article no. 15 (Technical briefs), 2015 (Data & Source code)

[20] Z. Lian*, J. Xiao. Automatic Shape Morphing for Chinese Characters, Siggraph Asia 2012, Article no. 2 (Technical briefs), 2012

[21] Z. Lian*, A. Godil, P.L. Rosin, X. Sun. A New Convexity Measurement for 3D Meshes, CVPR 2012, pp. 119-126, 2012


其他论文列表:(详细列表参见)

[1] J. Chen, Z. Lian*. TextPolar: Irregular Scene Text Detection using Polar Representation. International Journal on Document Analysis and Recognition (IJDAR). 24(4): 315-323, 2021.

[2] T. Sheng, Z. Lian*. Bidirectional Regression for Arbitrary-Shaped Text Detection. ICDAR 2021. 187-201.

[3] X. Sun, X. Long, D. He, S. Wen, Z. Lian*. VSRNet: End-to-End Video Segment Retrieval with Text Query. Pattern Recognition. 119: 108027, 2021.

[4] W. Wang, Z. Lian*, Y. Tang, J. Xiao. DeepStroke: Understanding Glyph Structure with Semantic Segmentation and Tabu Search. MMM 2020. 353-364.

[5] J. Liu, Z. Lian*, J. Xiao. Sketch based modeling and editing via shape space exploration. Multimedia Tools and Applications. 79(25-26): 18121-18142, 2020.

[6]  X. Sun, Z. Lian*. EasyMesh: An efficient method to reconstruct 3D mesh from a single image. Comput. Aided Geom. Des. 80: 101862, 2020.

[7] S. Tang, Z. Xia, Z. Lian*, Y. Tang, J. Xiao. FontRNN: Generating Large-scale Chinese Fonts via Recurrent Neural Network. Computer Graphics Forum (CGF). 38(7): 567-577, 2019 (presented at PG 2019).

[8] J. Chen, Z. Lian*, Y. Wang, Y. Tang, J. Xiao. Irregular Scene Text Detection via Attention Guided Border Labeling. SCIENCE CHINA (Information Sciences). 62: 220103, 2019.

[9] Y. Gao, Z. Lian*, Y. Tang, J. Xiao. Automatic Generation of Chinese Vector Fonts via Deep Layout Inferring. SIGGRAPH Asia 2019 Technical Briefs. 33-36.

[10] 高宜琛, 连宙辉*, 唐英敏, 肖建国. 一种新的矢量中文字库自动压缩方法. 图学学报, 42(3): 426-431, 2021.

[11] J. Liu, PL. Rosin, X. Sun, J. Xiao, Z. Lian*, Image-driven unsupervised 3D model co-segmentation, The Visual Computer (TVCJ), vol. 35, no. 6-8, pp. 909-920, 2019

[12] Y. Wang, Z. Lian*, Y. Tang, J. Xiao, Boosting Scene Character Recognition by Learning Canonical Forms of Glyphs,  International Journal on Document Analysis and Recognition (IJDAR), 2019 (to appear)

[13] D. Pickup, J. Liu, X. Sun, P. L. Rosin, R. R. Martin, Z. Cheng, Z. Lian, S. Nie, L. Jin, G. Shamai, Y. Sahillioğlu, L. Kavang. An Evaluation of Canonical Forms for Non-Rigid 3D Shape Retrieval, Graphical Models, 2018 (accepted)

[14] S. Yang, J. Liu, Z. Lian, Z. Guo. Text Effects Transfer via Distribution-Aware Texture Synthesis, Computer Vision and Image Understanding (CVIU), July 2018. (accepted)

[15] X. Chen, Z. Lian*, Y. Tang, J. Xiao. An Automatic Stroke Extraction Method using Manifold Learning. Eurographics 2017 (oral, short paper) (accepted)

[16] D. Liu, Z. Lian*, Y. Tang, J. Xiao. Structure-aware Image Resizing for Chinese Characters. MMM 2017 (oral, full paper) (accepted)

[17] W. Dong, Z. Lian*, Y. Tang, J. Xiao. Text Detection in Natural Images Using Localized Stroke Width Transform. MMM 2015, pp. 49-58, 2015

[18] J. Zhang, Z. Lian*, Z. Liu, J. Xiao. CEFM: A Heuristic Mesh Segmentation Method based on Convexity Estimation and Fast Marching. International Conference on Computer Graphics Theory and Applications (GRAPP 2015), pp. 114-121, 2015

[19] Z. Lian*, J. Zhang, et al. SHREC’15 Track: Non-rigid 3D Shape Retrieval. Eurographics Workshop on 3D Object Retrieval (3DOR), pp. 107-120, 2015

[20] W. Song, Z. Lian*, Y. Tang, J. Xiao. Content-Independent Font Recognition on a Single Chinese Character using Sparse Representation. ICDAR 2015, pp. 376-380, 2015

[21] X. Chen, Z. Lian*, Y. Tang, J. Xiao. A Benchmark For Stroke Extraction of Chinese Characters. Acta Scientiarum Naturalium Universitatis Pekinensis, 2015

[22] Y. Yi, Z. Lian*, Y. Tang, J. Xiao. A data-driven personalized digital ink for Chinese characters. MMM 2014, pp. 254-265, 2014 

[23] W. Pan, Z. Lian*, R. Sun, Y. Tang, J. Xiao. FlexiFont: A Flexible System to Generate Personal Font Libraries. DocEng 2014, pp. 17-20, 2014 

[24] W. Pan, Z. Lian*, Y. Tang, J. Xiao. Skeleton-Guided Vectorization of Chinese Calligraphy Images. MMSP 2014, paperID 19, 2014 

[25] H. Sun, Z. Lian*, Y. Tang, J. Xiao. Non-Rigid Point Set Registration For Chinese Characters Using Structure-Guided Coherent Point Drift. ICIP 2014, pp. 4752-4756, 2014 

[26] 易天旸,连宙辉*,孙浩,唐英敏,肖建国. 一种新的汉字笔画自动提取算法及其应用. 第十届中国计算机图形学大会(ChinaGraph 2014).

[27] C. Wang, Z. Lian*, Y. Tang, J. Xiao. Automatic Correspondence Finding for Chinese Characters using Graph Matching. The Seventh International Conference on Image and Graphics (ICIG 2013), pp. 545-550, 2013  

[28] 孙浩,唐英敏,连宙辉,肖建国. 汉字部件的无失真缩放变换方法研究. 计算机应用研究. 2012年10月

[29] Z. Lian*, A. Godil. A Feature-preserved Canonical Form for 3D Meshes, International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT), pp. 116-123. 2011(Oral)

[30] Z. Lian*, A. Godil, B. Bustos, M. Daoudi, J. Hermans, S. Kawamura, Y. Kurita, G. Lavoué, H.V. Nguyen, R. Ohbuchi, Y. Ohkita, Y. Ohishi, F. Porikli, M. Reuter, I. Sipiran, D. Smeets, P. Suetens, H. Tabia, D. Vandermeulen. SHREC’11 Track: Shape Retrieval on Non-rigid 3D Watertight Meshes. Eurographics Workshop on 3D Object Retrieval (3DOR), pp. 79-88, 2011

[31] Z. Lian*, A. Godil, X. Sun. Visual Similarity Based 3D Shape Retrieval Using Bag-of-Features, Shape Modeling International (SMI), pp. 25-36, 2010 (Oral)

[32] Z. Lian*, A. Godil, X. Sun, H. Zhang. Non-rigid 3D Shape Retrieval Using Multidimensional Scaling and Bag-of-Features, International Conference on Image Processing (ICIP), pp. 3181-3184, 2010

[33] Z. Lian*, A. Godil, T. Fabry, T. Furuya, J. Hermans, R. Ohbuchi, C. Shu, D. Smeets, P. Suetens, D. Vandermeulen, S. Wuhrer. SHREC’10 Track: Non-rigid 3D Shape Retrieval. Eurographics Workshop on 3D Object Retrieval (3DOR), pp. 101-108, 2010

[34] V.T. Porethi, A. Godil, H. Dutagaci, T. Furuya, Z. Lian, R. Ohbuchi. SHREC’10 Track: Generic 3D Warehouse. Eurographics Workshop on 3D Object Retrieval (3DOR), pp. 93-100, 2010

[35] A.M. Bronstein, M.M. Bronstein, U. Castellani, B. Falcidieno, A. Fusiello, A. Godil, L.J. Guibas, I. Kokkinos, Z. Lian, M. Ovsjanikov, G. Patanè, M. Spagnuolo, R. Toldo. SHREC’10 Track: Robust Shape Retrieval. Eurographics Workshop on 3D Object Retrieval (3DOR), pp. 71-78, 2010

[36] R.C. Veltkamp, G. Giezeman, H. Bast, T. Baumbach, T. Furuya, J. Giesen, A. Godil, Z. Lian, R. Ohbuchi, W. Saleem. SHREC’10 Track: Large-scale Retrieval. Eurographics Workshop on 3D Object Retrieval (3DOR), pp. 63-69, 2010 

[37] A. Godil, H. Dutagaci, C. Akgül, A. Axenopoulos, B. Bustos, M. Chaouch, P. Daras, T. Furuya, S. Kreft, Z. Lian, T. Napoleon, A. Mademlis, R. Ohbuchi, P. Rosin, B. Sankur, T. Schreck, X. Sun, M. Tezuka, A. Verroust-Blondet, M. Walter, Y. Yemez. SHREC’09 Track: Generic Shape Retrieval. Eurographics Workshop on 3D Object Retrieval (3DOR), pp. 62-68, 2009

[38] Z. Lian*, P.L. Rosin, X. Sun. A Rectilinearity Measurement for 3D Meshes. ACM International Conference on Multimedia Information Retrieval (MIR), pp. 395-402, 2008 (Oral)


专利列表(已授权19项):

[1] 潘琬琼,连宙辉,唐英敏,肖建国. 一种快速制作矢量字库的方法及系统. 国家发明专利201310407337.X(已授权)

[2] 潘琬琼,连宙辉,唐英敏,肖建国. 一种基于骨架指导的文字图像矢量化方法及系统. 国家发明专利201410047304.3(已授权)

[3] 易天旸,连宙辉,唐英敏,肖建国. 一种个性化汉字数字墨水的生成方法. 国家发明专利201310407336.5(已授权)

[4] 董文妍,连宙辉,唐英敏,肖建国. 基于局部笔画宽度变换的自然场景图片中文本检测方法. 国家发明专利201410026091.6(已授权)

[5] 孙浩,连宙辉,唐英敏,肖建国. 一种面向矢量字形的汉字笔画自动提取技术. 国家发明专利201510303067.7(已授权)

[6] 赵波,连宙辉,唐英敏,肖建国. 一种基于风格学习的汉字合成方法. 国家发明专利201510696769.6(已授权)

[7] 刘成东,连宙辉,唐英敏,肖建国. 一种中文字符缩放方法. 国家发明专利201610422723.X

[8] 刘成东,连宙辉,唐英敏,肖建国. 一种字符缩放方法. 国家发明专利201610816680.3

[9] 连宙辉,肖建国. 一种基于书写风格建模的中文字库自动生成方法. 国家发明专利201610828454.7(已授权)

等….


成果转化案例:

  1. 2018年3月,与方正手迹公司签署技术转让合同,该公司专注于提供个性化中文字库的制作和使用服务,本研究团队面向“中文字库”方面的研究成果全面注入该企业,中文字库智能化辅助设计与自动生成、中文字库自动压缩等技术已经投入实用,产生良好的经济和社会效益。



目前主持的科研项目:

国家自然科学基金面上资助(62372015):“基于生成模型的汉字形状建模与图像合成方法研究”(2024.1 ~ 2027.12)


主持过的科研项目:

北京市科技新星计划(Z191100001119077):“高质量大规模中文字库辅助设计与自动生成技术研究”(2019.11 ~ 2022.10)

国家自然科学基金面上资助(61672043):“基于标准形态与稀疏表示的非刚性三维形状检索方法研究”(2017.1 ~ 2020.12)

国家语委重点项目(ZDI135-9):“中文字库智能化辅助设计技术研究”(2016.1 ~ 2018.12)

国家自然科学基金青年科学基金(61202230):“基于形状分析与处理的高质量中文字库自动生成方法研究”(2013.1 ~ 2015.12)

中国博士后科学基金特别资助(2013T60038):“手写体计算机中文字库自动生成的关键技术研究”(2013.1 ~ 2014.7)

中国博士后科学基金面上资助(2012M510274):“非刚性三维形状检索的若干关键技术研究”(2011.7 ~ 2013.6)

 

目前参与的科研项目:

国家自然科学基金面上资助(61672056):“汉字字体流形构建方法研究”(2017.1 ~ 2020.12)

国家自然科学基金面上资助(61472015):“基于深度学习的汉字书写风格建模与重建方法研究”(2015.1 ~ 2018.12)

北京市自然科学基金面上资助(4152022):“基于风格建模的手写体中文字库自动生成方法研究(2015.1 ~ 2017.12)


主要奖励:

2023年北京市技术发明奖二等奖(排名1)

2022年北京大学黄廷方/信和青年杰出学者奖

2021年北京大学第二十一届青年教师教学基本功比赛(理工科类)优秀指导教师奖

2021年中国专利优秀奖(排名第一)

2020/2021年CVPR杰出审稿人

2019年中国人工智能学会吴文俊人工智能优秀青年奖

2019年北京大学第四届产学研合作奖优秀项目奖一等奖(排名第一)

2018年度“王选青年教师奖”一等奖

2014年北京大学第十四届青年教师教学基本功比赛(理工科类)一等奖

2012年度北京大学优秀博士后


学术活动:

NeurIPS 领域主席AC (2023)

CVPR 领域主席AC (2023)

ICCV 领域主席AC (2021)

AAAI 高级程序委员会委员SPC (2022)

IJCAI 高级程序委员会委员SPC (2021)

IJCV、TPAMI、ACM Transactions on Graphics、TIP、TMM、Pattern Recognition、IJCAI、Multimedia Systems、Parallel Computing、Computers & Graphics、The Visual Computer,International Journal of Machine Learning and Cybernetics, 自动化学报、浙江大学学报(英文版)等学术杂志与会议审稿人

ACM/IEEE/CAAI会员 CCF/CSIG高级会员

CCF计算机视觉专业委员会委员

人工智能学会模式识别专委会委员

中国图象图形学学会文档图像分析与识别专委会委员/常务委员

中国图象图形学学会机器视觉专委会委员

CCF全国文字与计算学术研讨会程序委员会委员

ECCV PC member(2020)

AAAI PC member(2020,2021)

ICCV PC member(2019,2021)

CVPR PC member (2017,2018,2019, 2020, 2021)

MM PC member(2019,2020, 2021)

Eurographics Workshop on 3D Object Retrieval (EG 3DOR) PC member (2017,2018,2019,2020,2021)

ICIP PC member (2017)

ICDAR PC member (2017,2019, 2021)

ACCV PC member (2018)

回到顶部