连宙辉
长聘副教授、研究员、博士生导师
1985年5月出生于福建福州。北京大学王选计算机研究所长聘副教授/研究员/博导（2026.2~），北京大学王选计算机研究所副教授/博导（2015.8~2026.1），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国家公派联合培养博士生（2008.1~2009.1）。2011年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，2005年本科毕业于南京航空航天大学自动化学院。
现任中国图像图形学会三维视觉专委会秘书长，中国文字字体设计与研究中心副主任，入选国家级青年人才计划（2022）、国家语言文字关键研究领域领航计划（2024）和北京市科技新星计划（2019）。研究领域为计算机图形学、计算机视觉、人工智能，主要研究方向是图形图像生成、三维视觉、具身智能与空间智能，在领域重要期刊（TOG, TPAMI, IJCV等）和会议（SIGGRAPH/SIGGRAPH Asia, CVPR, ICRA等）上发表论文100多篇。多次担任CVPR、ICCV、ICML、ICLR、NeurIPS、ECCV、SIGGRAPH Asia等国际会议领域主席（或相当职务），获北京市技术发明奖二等奖（排名1）、中国专利优秀奖（排名1）、ICRA 2024服务机器人最佳论文候选、吴文俊人工智能优秀青年奖、北京大学黄廷方/信和青年杰出学者奖、北京大学-中国光谷成果转化奖、北京大学教学成果一等奖、北京大学青年教师教学基本功比赛一等奖等奖励。
代表性成果：
1、图形图像生成方向：提出一系列可视内容生成新技术新方法，并重点面向字体设计制作应用需求，研发中文字体智能计算与自动生成技术及系统（EasyFont、SCFont、DeepVecFont、HFH-Font、UTDesign等），实现汉字字形的高效建模与自动生成，解决“海量汉字字体如何进入计算机”的难题，满足各类应用场景对于海量中文字体的迫切需求，相关技术和系统广泛落地应用，获北京市技术发明奖二等奖（排名1）、中国专利优秀奖（排名1）。
2、具身智能与空间智能方向：长期深耕三维视觉、场景重建与生成式仿真，为具身智能提供空间理解与环境建模底座，提出一系列“境一物一人”三维重建与生成方法，推动仿真世界模型从几何精确走向物理真实，实现机器人/机械臂/无人机的具身操作与导航。构建室内无人机视觉语言导航测试基准（IndoorUAV），实现基于VLA/WAM 的无人机具身导航；提出多个基于单目视觉的三维场景重建方法（Pano2Room、ActMVS、MoonSplat等），实现高效便捷三维场景重建；设计高质量数字人编辑生成算法（ADGAN、DCT-Net、FISHuman等），多次入选CVPR Oral/Highlight/Spotlight；研发书法临摹机器人（CalliRewrite），获顶级会议ICRA 2024服务机器人最佳论文候选。
代表性论文（*表示通讯作者）：
会议:
[1] X. Liu, Y. Liu, H. Qiu, Q. Yang, Z. Lian*. IndoorUAV: Benchmarking vision-language UAV navigation in continuous indoor environments. AAAI 2026
[2] H. Liu, Y. Men, Z. Lian*. FISHuman: Fine-grained Single-image 3D Human Reconstruction via Multi-view 4D Remeshing. CVPR 2026 (Highlight)
[3] G. Pu, Y. Han, H. Li, Y. Zhang, H. Zhou, Z. Lian*. MoonSplat: Monocular Online Gaussian Splatting with Sim (3) Global Optimization. SIGGRAPH 2026
[4] G. Pu, Y. Han, Z. Lian*. ActMVS: Active Scene Reconstruction with Monocular Multi-View Stereo. ICRA 2026
[5] H. Cai, Y. Luo, Z. Lian*. Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation. CVPR 2026
[6] Y. Luo, P. Zhang, X. Zhang, X. Guo, Z. Lian*, Y. Lu. SciForma: Structure-Faithful Generation of Scientific Diagrams. SIGGRAPH Asia 2026
[7] H. Liu, Y. Men, Z. Lian*. Creating Your Editable 3D Photorealistic Avatar with Tetrahedron-constrained Gaussian Splatting. CVPR 2025 (Highlight)
[8] B. Xiong, J. Liu, J. Hu, C. Wu, J. Wu, X. Liu, C. Zhao, E. Ding, Z. Lian*. TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting. CVPR 2025
[9] Y. Zhao, Y. Gao, Y. Luo, J. Duan, S. Lin, L. Xiong, Z. Lian*. UTDesign: A Unified Framework for Stylized Text Editing and Generation in Graphic Design Images. SIGGRAPH Asia 2025
[10] Y. Liu, Z. Lian*, QT-Font: High-efficiency Font Synthesis via Quadtree-based Diffusion Models. SIGGRAPH 2024
[11] G. Pu, Y. Zhao, Z. Lian*, Pano2Room: Novel View Synthesis from a Single Indoor Panorama. SIGGRAPH Asia 2024
[12] Y. Luo, Z. Wu, Z. Lian*, CalliRewrite: Recovering Handwriting Behaviors from Calligraphy Images without Supervision, ICRA 2024 (Selected as a Finalist of IEEE ICRA Best Paper Award in Service Robotics)
[13] G. Pu, P.-S. Wang, Z. Lian*. SinMPI: Novel View Synthesis from a Single Image with Expanded Multiplane Images. SIGGRAPH Asia 2023
[14] Y. Wang, Y. Wang, L. Yu, Y. Zhu, Z. Lian*. DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality. CVPR 2023
[15] Z. Xia, B. Xiong, Z. Lian*. VecFontSDF: Learning to Reconstruct and Synthesize High-quality Vector Fonts via Signed Distance Functions. CVPR 2023
[16] 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
[17] Y. Men, Y. Yao, M. Cui, Z. Lian, X. Xie, X. Hua. Unpaired Cartoon Image Synthesis via Gated Cycle Mapping. CVPR 2022
[18] T. Sheng, J. Chen, Z. Lian*. CentripetalText: An Efficient Text Instance Representation for Scene Text Detection, NeurIPS 2021
[19] Y. Gao, F. Wei, J. Bao, S. Gu, D. Chen, F. Wen, Z. Lian*. High-Fidelity and Arbitrary Face Editing, CVPR 2021
[20] X. Zhang, X. Sun, Z. Lian*. BoW Pooling: A Plug-and-Play Unit for Feature Aggregation of Point Clouds, AAAI 2021
[21] Y. Liu, Z. Lian*. FontRL: Chinese Font Synthesis via Deep Reinforcement Learning, AAAI 2021
[22] Y. Men, Y. Mao, Y. Jiang, W. Ma, Z. Lian*, Controllable Person Image Synthesis with Attribute-Decomposed GAN. CVPR 2020 (Oral)
[23] Y. Men, Z. Lian*, Y. Tang, J. Xiao. DynTypo: Example-based Dynamic Text Effects Transfer, CVPR 2019
[24] 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
[25] Y. Jiang,Z. Lian*, Y. Tang, J. Xiao. SCFont: Structure-guided Chinese Font Generation via Deep Stacked Networks. AAAI 2019
[26] Y. Men, Z. Lian*, Y. Tang, J. Xiao. A Common Framework for Interactive Texture Transfer. CVPR 2018 (Spotlight)
[27] J. Liu, Z. Lian*, Y. Wang, J. Xiao. Incremental Kernel Null Space Discriminant Analysis for Novelty Detection. CVPR 2017 (Data & Source code)
[28] S. Yang, J. Liu, Z. Lian, Z. Guo. Awesome Typography: Statistics-Based Text Effects Transfer. CVPR 2017
[29] 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
[30] R. Sun, Z. Lian*, Y. Tang, J. Xiao. Aesthetic Visual Quality Evaluation of Chinese Handwritings. IJCAI 2015, pp. 2510-2516, 2015 (Data & Source code)
[31] 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)
[32] Z. Lian*, J. Xiao. Automatic Shape Morphing for Chinese Characters, Siggraph Asia 2012, Article no. 2 (Technical briefs), 2012
[33] Z. Lian*, A. Godil, P.L. Rosin, X. Sun. A New Convexity Measurement for 3D Meshes, CVPR 2012, pp. 119-126, 2012
期刊：
[1] H. Li, Z. Lian*, HFH-Font: Few-shot Chinese Font Synthesis with Higher Quality, Faster Speed, and Higher Resolution, ACM Transactions on Graphics (TOG) (presented at SIGGRAPH Asia 2024)
[2] 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
[3] 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)
[4] 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)
[5] 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)
[6] 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)
[7] 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)
[8] 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
[9] Z. Lian*, Y. Gao. CVFont: Synthesizing Chinese Vector Fonts via Deep Layout Inferring, Computer Graphics Forum (CGF), 2022 (Accepted)
[10] 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)
[11] 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
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)
主要奖励：
2026年北京大学教学优秀奖
2025年北京大学教学成果奖一等奖
2024年ICRA 2024服务机器人最佳论文候选（通讯作者）
2024年北京大学-中国光谷成果转化奖（排名1）
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：
中国图像图形学会三维视觉专委会秘书长/常务委员
China3DV程序委员会主席/组织委员会主席（2025，2026）
SIGGRAPH Asia TPC (2025)
ICML 领域主席AC (2025，2026）
ICLR领域主席AC (2027)
NeurIPS 领域主席AC (2023，2024，2025，2026)
CVPR 领域主席AC (2023)
ICCV 领域主席AC (2021，2025)
ECCV 领域主席AC (2026)
AAAI 高级程序委员会委员SPC (2022，2026)
IJCAI 高级程序委员会委员SPC (2021)
《Pattern Recognition》期刊编委
《计算机辅助设计与图形学学报》期刊编委
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
中国图像图形学会文档图像分析与识别专委会委员/常务委员