Prof. Yu-Kun Lai

Professor Director of Research School of Computer Science and Informatics Cardiff University, Wales, UK Contact Info Office: S/3.06 Queen's Buildings, 5 The Parade, Roath, Cardiff CF24 3AA Tel: +44 (0) 29 20876353 Email: Yukun.Lai (at) cs.cardiff.ac.uk Publications   Teaching    Prizes and Honours  Education      CV

Professional Activities        

I am on the editorial boards of Computer Graphics Forum and The Visual Computer.

I was conference co-chair of Computation Visual Media (CVM) 2016 and Eurographics Symposium on Geometry Processing (SGP) 2014.

I have been on the programme committee of

• ACM Symposium on Solid and Physical Modeling (ACM SPM, SIAM GD/SPM) 2012-2020
• Eurographics Symposium on Geometry Processing (SGP) 2014, 2015, 2017-2020
• Geometric Modeling and Processing (GMP) 2012, 2014-2018
• Computer Graphics International (CGI) 2018, 2019, 2020
• Computational Visual Media (CVM) 2012, 2013, 2015, 2017, 2018, 2019, 2020
• Pacific Graphics (PG) 2012, 2015-2018
• CAD/Graphics 2011, 2013, 2015, 2017
• SIGGRAPH Asia Technical Briefs & Posters 2014-2016
• Expressive 2014-2016, 2018, 2019
• British Machine Vision Conference 2015-2017 (reviewer), 2018-2020 (Area Chair)
• Eurographics 2011 short papers
• International Symposium on Visual Computing (ISVC) 2018, 2019, 2020
• Computer Animation and Social Agents (CASA) 2010

I am also a regular reviewer for major journals/conferences in computer graphics, computer vision and geometric modelling.

Along with my colleagues, I am organsing 3DOR (3D Object Retrieval) 2021 workshop.

Along with my colleagues, I am organsing China-UK Workshop on Visual Signal Cognition and Understanding.

Research Interests

• Computer Graphics
• Geometry Processing
• Computer Vision
• Image Processing

In other words, my research interests include creating nice images/shapes/animation automatically or with a small amount of user interaction and developing automatic algorithms to understand and analyse visual data and present data in an interesting manner.

If you are an undergraduate or master student interested in doing research in these exciting and highly rewarded fields, send me an email.

Some potential projects (but more are possible).

• 3D Shape Analysis using Deep Learning

  PROJECT TITLE: 3D Shape Analysis using Deep Learning

  KEYWORDS:3D geometry, machine learning, convolutional neural networks, shape

  DESCRIPTION:3D shapes have proliferated in recent years, due to the availability of low-cost 3D cameras such as Kinect and Occipital Structure sensors, and their wide applicability in manufacturing design, entertainment industry, digital earth, 3D printing, and virtual reality etc. Online databases such as Trimble 3D Warehouse contain millions of 3D shapes. It is an increasing challenge to describe complicated 3D shapes effectively and analyse shapes at a high-level, e.g. to recognise objects in a scene or to find reusable parts for manufacturing design. Deep learning has shown to be an effective approach in image analysis, achieving state-of-the-art performance in many tasks. The aim of the project is to develop deep learning techniques for 3D shape analysis.

• 3D Model Segmentation and Analysis

  PROJECT TITLE: 3D Model Segmentation and Analysis

  KEYWORDS: geometric models, shape analysis, segmentation, computer graphics, computer-aided design

  DESCRIPTION: With the development of 3D acquisition techniques, 3D models are now widely available and used in various applications. The demand for model analysis and understanding is thus ever increasing. Model segmentation, i.e. decomposing a model into a set of disjoint, meaning pieces (e.g. limbs and torso of an animal) or ones which satisfy other desirable criteria (e.g. with consistent shape or texture constraint). Model segmentation is an important step towards model understanding and has broad applications, such as reverse engineering in computer-aided geometric design, as well as simplification, collision detection, morphing and animation in computer graphics. This project aims at investigating effective and efficient solutions to model segmentation, using various computer vision techniques.

• Image and Video Vectorisation

PROJECT TITLE: Image and Video Vectorisation

KEYWORDS: image and video processing, computer graphics, image compression, image editing

DESCRIPTION: Vector graphics are well-known to offer various advantages over raster graphics. Many images, ranging from artistic work to captured photos, have relatively uniform or smoothly changing colours, and representing them using vector graphics can lead to significant savings of storage and network bandwidth. They are also resolution-independent and easy to edit, making them particularly suitable for animation transmitted over the Internet, such as SVG and Shockwave Flash. Manual creation of vectorised graphics takes a huge amount of time. The aim of this project is to investigate robust and efficient solutions to computer aided generation of vectorised images and videos.

• Modelling and Transferring Geometric Details over 3D Shapes

  PROJECT TITLE: Modelling and Transferring Geometric Details over 3D Shapes

  KEYWORDS: geometric models, shape analysis, computer graphics, computer vision

  DESCRIPTION: The recent development of 3D acquisition techniques allows complicated geometric models with fine details to be digitally captured. In many cases, such details reveal the essential geometric textures or the particular artistic styles (e.g. sculpture, woodcut etc.) of the objects. Modelling geometric textures or styles from one object makes it possible to reproduce similar textures or styles over new models. This not only brings richness to new objects, but also allows newly created objects to be stylised as exemplars. In this project, shape analysis and computer vision techniques will be utilised to appropriately analyse and model the geometric details and further algorithms to transfer such models will be investigated.

If you are interested in applying for CSC funding: Cardiff University is an official partner of China Scholarship Council (CSC). There are schemes for joint funding with tuition fees waived. If you are interested in applying for CSC funding, please discuss this with me as additional deadline/steps may apply.

Teaching Activities

I teach the following modules in the academic year 2019/20:

• CM1208 Maths for Computer Science
• CMT205 Object Oriented Development with Java (shared with Dr. M.J.W. Morgan and Dr. Y. Li)
• CMT307 Applied Machine Learning (shared with Dr. J. Camacho Collados and Dr. Y. Li)

2020

		Line Drawings for Face Portraits from Photos using Global and Local Structure based GANs Ran Yi, Mengfei Xia, Yong-Jin Liu,, Yu-Kun Lai, Paul L. Rosin IEEE Transactions on Pattern Analysis and Machine Intelligence, to appear. [paper] [code] [doi]
		Noise-Resilient Reconstruction of Panoramas and 3D Scenes using Robot-Mounted Unsynchronized Commodity RGB-D Cameras Sheng Yang, Beichen Li, Yan-Pei Cao, Hongbo Fu, Yu-Kun Lai, Leif Kobbelt, Shi-Min Hu ACM Transactions on Graphics, to appear. [paper] [doi]
		Feature-Aware Uniform Tessellations on Video Manifold for Content-Sensitive Supervoxels Ran Yi, Zipeng Ye, Wang Zhao, Minjing Yu, Yu-Kun Lai, Yong-Jin Liu IEEE Transactions on Pattern Analysis and Machine Intelligence, to appear. [paper] [code] [doi]
		A survey on deep geometry learning: from a representation perspective Yun-Peng Xiao, Yu-Kun Lai, Fang-Lue Zhang, Chunpeng Li, Lin Gao Computational Visual Media, vol. 6(2), pp. 113-133. [paper] [doi]
		PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models Lin Gao, Ling-Xiao Zhang, Hsien-Yu Meng, Yi-Hui Ren, Yu-Kun Lai, Leif Kobbelt IEEE Transactions on Visualization and Computer Graphics, to appear. [paper]
		Sparse Graph Regularized Mesh Color Edit Propagation Bo Li, Yu-Kun Lai, Paul L. Rosin IEEE Transactions on Image Processing, to appear. [paper] [doi]
		Learning to Reconstruct and Understand Indoor Scenes From Sparse Views Jingyu Yang, Ji Xu, Kun Li, Yu-Kun Lai, Huanjing Yue, Jianzhi Lu, Hao Wu, Yebin Liu IEEE Transactions on Image Processing, vol. 29, pp. 5753-5766, 2020. [paper] [doi]
		Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping Ran Yi, Yong-Jin Liu, Yu-Kun Lai, Paul L. Rosin IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) [paper] [code] [official version]
		MLCVNet: Multi-Level Context VoteNet for 3D Object Detection Qian Xie, Yu-Kun Lai, Jing Wu, Zhoutao Wang, Yiming Zhang, Kai Xu, Jun Wang IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) [paper] [code] [official version]
		Ranking-Preserving Cross-Source Learning for Image Retargeting Quality Assessment Yong-Jin Liu, Yiheng Han, Zipeng Ye, Yu-Kun Lai IEEE Transactions on Pattern Analysis and Machine Intelligence, to appear. [paper] [code] [doi]
		Sparse Data Driven Mesh Deformation Lin Gao, Yu-Kun Lai, Jie Yang, Ling-Xiao Zhang, Shihong Xia, Leif Kobbelt IEEE Transactions on Visualization and Computer Graphics, to appear [paper] [doi] [video]
		Content-Preserving Image Stitching with Piecewise Rectangular Boundary Constraints Yun Zhang, Yu-Kun Lai, Fang-Lue Zhang IEEE Transactions on Visualization and Computer Graphics, to appear [paper] [doi]
		Active Arrangement of Small Objects in 3D Indoor Scenes Suiyun Zhang, Zhizhong Han, Yu-Kun Lai, Matthias Zwicker, Hui Zhang IEEE Transactions on Visualization and Computer Graphics, to appear [paper] [doi]
		HeteroFusion: Dense Scene Reconstruction Integrating Multi-sensors Sheng Yang, Beichen Li, Minghua Liu, Yu-Kun Lai, Leif Kobbelt, Shi-Min Hu IEEE Transactions on Visualization and Computer Graphics, to appear. [paper] [supplementary] [video] [doi]
		Semantic Labeling and Instance Segmentation of 3D Point Clouds using Patch Context Analysis and Multiscale Processing Shi-Min Hu, Jun-Xiong Cai, Yu-Kun Lai IEEE Transactions on Visualization and Computer Graphics, vol. 26(7), pp. 2485-2498, 2020. [paper] [doi]
		Structure-Preserving Neural Style Transfer Ming-Ming Cheng, Xiao-Chang Liu, Jie Wang, Shao-Ping Lu, Yu-Kun Lai, Paul L. Rosin IEEE Transactions on Image Processing, vol. 29, pp. 909-920, 2020 [paper] [doi]
		WSCNet: Weakly Supervised Coupled Networks for Visual Sentiment Classification and Detection Dongyu She, Jufeng Yang, Ming-Ming Cheng, Yu-Kun Lai, Paul L. Rosin, Liang Wang IEEE Transactions on Multimedia, to appear [paper] [doi]
		Sparse MDMO: Learning a Discriminative Feature for Micro-Expression Recognition Yong-Jin Liu, Bing-Jun Li, Yu-Kun Lai IEEE Transactions on Affective Computing, to appear [paper] [doi] [code]
		Spatio-Temporal Reconstruction for 3D Motion Recovery Jingyu Yang, Xin Guo, Kun Li, Meiyuan Wang, Yu-Kun Lai, Feng Wu IEEE Transactions on Circuits and Systems for Video Technology, to appear [paper] [doi]

Other Publications:

• Y.-J. Yuan, Y.-K. Lai, J. Yang, Q. Duan, H. Fu, L. Gao, Mesh variational autoencoders with edge contraction pooling, IEEE CVPR Workshop, 2020. [paper] [official version]
• J. Zhang, C. Li, Q. Song, L. Gao, Y.-K. Lai, Automatic 3D tooth segmentation using convolutional neural networks in harmonic parameter space, Graphical Models, vol. 109, 101071, 2020. [paper] [doi]

2019

		RGB-D Image Analysis and Processing Editors: Paul L. Rosin, Yu-Kun Lai, Ling Shao, Yonghuai Liu Springer, ISBN 978-3-030-28603-3, 2019. [publisher]
		SDM-NET: Deep Generative Network for Structured Deformable Mesh Lin Gao, Jie Yang, Tong Wu, Yu-Jie Yuan, Hongbo Fu, Yu-Kun Lai, Hao Zhang ACM Transactions on Graphics, vol. 38(6), pp. 243, 2019. [paper] [doi] [video] [project]
		Robust non-rigid registration with reweighted position and transformation sparsity Kun Li, Jingyu Yang, Yu-Kun Lai, Daoliang Guo IEEE Transactions on Visualization and Computer Graphics, vol. 25(6), pp. 2255-2269, 2019. [paper] [doi]
		Automatic Example-based Image Colorization using Location-Aware Cross-Scale Matching Bo Li, Yu-Kun Lai, Matthew John, Paul L. Rosin IEEE Transactions on Image Processing, vol. 28(9), pp. 4606-4619, 2019. [paper] [doi]
		Global 3D Non-Rigid Registration of Deformable Objects Using a Single RGB-D Camera Jingyu Yang, Daoliang Guo, Kun Li, Zhenchao Wu, Yu-Kun Lai IEEE Transactions on Image Processing, vol. 28(10), pp. 4746-4761, 2019. [paper] [doi]
		When facial expressions do and do not signal minds: The role of face inversion, expression dynamism, and emotion type Eva G. Krumhuber, Yu-Kun Lai, Paul L. Rosin, Kurt Hugenberg Emotion, vol. 19(4), pp. 746-750, 2019. [paper] [doi]
		APDrawingGAN: Generating Artistic Portrait Drawings from Face Photo swith Hierarchical GANs Ran Yi, Yong-Jin Liu, Yu-Kun Lai, Paul L. Rosin IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2019 (oral). [paper] [supplementary] [official version]
		IP102: A Large-Scale Benchmark Dataset for Insect Pest Recognition Xiaoping Wu, Chi Zhan, Yu-Kun Lai, Ming-Ming Cheng, Jufeng Yang IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2019 (oral). [paper] [dataset] [official version]
		SketchGAN: Joint Sketch Completion and Recognition with Generative Adversarial Network Fang Liu, Xiaoming Deng, Yu-Kun Lai, Yong-Jin Liu, Cuixia Ma, Hongan Wang IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [paper] [official version]
		VV-NET: Voxel VAE Net with Group Convolutions for Point Cloud Segmentation Hsien-Yu Meng, Lin Gao, Yu-Kun Lai, Dinesh Manocha IEEE/CVF International Conference on Computer Vision (ICCV), 2019. [paper] [official version]
		Joint Acne Image Grading and Counting via Label Distribution Learning Xiaoping Wu, Ni Wen, Jie Liang, Yu-Kun Lai, Dongyu She, Ming-Ming Cheng, Jufeng Yang IEEE/CVF International Conference on Computer Vision (ICCV), 2019. [paper] [official version]
		Attention-Aware Polarity Sensitive Embedding for Affective Image Retrieval Xingxu Yao, Dongyu She, Sicheng Zhao, Jie Liang, Yu-Kun Lai, Jufeng Yang IEEE/CVF International Conference on Computer Vision (ICCV), 2019. [paper] [official version]
		ClusterSLAM: A SLAM Backend for Simultaneous Rigid Body Clustering and Motion Estimation Jiahui Huang, Sheng Yang, Zishuo Zhao, Yu-Kun Lai, Shi-Min Hu IEEE/CVF International Conference on Computer Vision (ICCV), 2019. [paper] [official version]
		Probabilistic Projective Association and Semantic Guided Relocalization for Dense Reconstruction Sheng Yang, Zheng-Fei Kuang, Yan-Pei Cao, Yu-Kun Lai, Shi-Min Hu International Conference on Robotics and Automation (ICRA), 2019. [paper] [doi]

Other Publications:

• K. Li, J. Liu, Y.-K. Lai, J. Yang, Generating 3D faces using multi-column graph convolutional networks, Computer Graphics Forum, vol. 38(7), pp. 215-224, 2019. [paper] [doi]
• H.-H. Zhao, P. L. Rosin, Y.-K. Lai, Block compressive sensing for solder joint images with wavelet packet thresholding, IEEE Transactions on Components, Packaging and Manufacturing Technology, vol. 9(6), pp. 1190-1199, 2019. [paper] [doi]
• Y.-J. Yuan, Y.-K. Lai, T. Wu, S. Xia, L. Gao, Data-driven weight optimization for real-time mesh deformation, Graphical Models, vol. 104, 2019. [paper] [doi]
• J.-X. Cai, T.-J. Mu, Y.-K. Lai, S.-M. Hu, Deep point-based scene labelling with depth mapping and geometric patch feature encoding, Graphical Models, vol. 104, 2019. [paper] [doi]
• T. Wang, D. George, Y.-K. Lai, X. Xie, G. K.L. Tam, Consistent segment-wise matching with multi-layer graphs, Computer Aided Geometric Design, vol. 70, pp. 31-45, 2019. [paper] [doi]
• R. Dyke, Y.-K. Lai, P. L. Rosin, G. K.L. Tam, Non-rigid registration under anisotropic deformations, Computer Aided Geometric Design, vol. 71, pp. 142-156, 2019. [paper] [doi]
• S. Zhang, Z. Han, Y.-K. Lai, M. Zwicker, H. Zhang, Stylistic scene enhancement GAN: mixed stylistic enhancement generation for 3D indoor scenes, The Visual Computer, vol. 35(6-8), pp. 1157-1169, 2019. [paper] [doi]
• Y. Zhang, Y.-K. Lai, F.-L. Zhang, Stereoscopic image stitching with rectangular boundaries, The Visual Computer, vol. 35(6-8), pp. 823-835, 2019. [paper] [doi]
• H.-H. Zhao, P. L. Rosin, Y.-K. Lai, J.-H. Zheng, Y.-N. Wang, Adaptive gradient-based block compressive sensing with sparsity for noisy images, Multimedia Tools and Applications, to appear. [paper] [doi]
• Y. Liu, Y.-K. Lai, Z. Wang, H. Yan, A new learning approach to malware classification using discriminative feature extraction, IEEE Access, vol. 7, pp. 13015-13023, 2019. [paper] [doi]
• Z. Wu, K. Li, Y.-K. Lai, J. Yang, Global as-conformal-as-possible non-rigid registration of multi-view scans, IEEE International Conference on Multimedia and Expo (ICME), 2019. [paper] [doi]
• C. Yuan, K. Li, Y.-K. Lai, Y. Liu, J. Yang, 3D face representation and reconstruction with multi-scale graph convolutional autoencoders, IEEE International Conference on Multimedia and Expo (ICME), 2019. [paper] [doi]
• R. M. Dyke, C. Stride, Y.-K. Lai, P. L. Rosin, et al. SHREC'19: Shape Correspondence with Isometric and Non-Isometric Deformations, Eurographics Workshop on 3D Object Retrieval (3DOR), 2019. [paper] [doi] [dataset]

2018

		Automatic Unpaired Shape Deformation Transfer Lin Gao, Jie Yang, Yi-Ling Qiao, Yu-Kun Lai, Paul L. Rosin, Weiwei Xu, Shihong Xia ACM Transactions on Graphics, vol. 37(6), 237:1-15 [paper] [video]
		Virtual Recovery of Content from X-Ray Micro-Tomography Scans of Damaged Historic Scrolls Paul L. Rosin, Yu-Kun Lai, Chang Liu, Graham R. Davies, David Mill, Gary Tuson, Yuki Russell Scientific Reports, vol. 8, pp. 11901 [paper] [doi] [news]
		Recognition from Web Data: A Progressive Filtering Approach Jufeng Yang, Xiaoxiao Sun, Yu-Kun Lai, Liang Zheng and Ming-Ming Cheng IEEE Transactions on Image Processing, vol. 27(11), pp. 5303-5315, 2018. [paper] [doi]
		Bi-harmonic deformation transfer with automatic key point selection Jie Yang, Lin Gao, Yu-Kun Lai, Paul L. Rosin, Shihong Xia Graphical Models, vol. 98, pp. 1-13, 2018 [paper] [doi]
		Knowledge graph construction with structure and parameter learning for indoor scene design Yuan Liang, Fei Xu, Song-Hai Zhang, Yu-Kun Lai, Taijiang Mu Computational Visual Media, vol. 4(2), pp. 123-137, 2018 [paper] [doi]
		Weakly Supervised Coupled Networks for Visual Sentiment Analysis Jufeng Yang, Dongyu She, Yu-Kun Lai, Paul L. Rosin, Ming-Hsuan Yang IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (spotlight), 2018 [paper] [official version]
		Content-Sensitive Supervoxels via Uniform Tessellations on Video Manifolds Ran Yi, Yong-Jin Liu, Yu-Kun Lai IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 [paper] [official version] [code]
		CartoonGAN: Generative Adversarial Networks for Photo Cartoonization Yang Chen, Yu-Kun Lai, Yong-Jin Liu IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 [paper] [official version] [trained models]
		Variational Autoencoders for Deforming 3D Mesh Models Qingyang Tan, Lin Gao, Yu-Kun Lai, Shihong Xia IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 [paper] [official version]  [arXiv preprint]
		Alive Caricature from 2D to 3D Qianyi Wu, Juyong Zhang, Yu-Kun Lai, Jianmin Zheng, Jianfei Cai IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (spotlight), 2018 [paper] [official version]  [arXiv preprint]
		Robust Virtual Unrolling of Historical Parchment XMT Images Chang Liu, Paul L. Rosin, Yu-Kun Lai, Weiduo Hu IEEE Transactions on Image Processing, vol. 27(4), pp. 1914-1926, 2018. [paper] [doi]
		Online low-rank representation learning for joint multi-subspace recovery and clustering Bo Li, Risheng Liu, Junjie Cao, Jie Zhang, Yu-Kun Lai, Xiuping Liu IEEE Transactions on Image Processing, vol. 27(1), pp. 335-348, 2018 [paper] [doi]
		Scribble-based gradient mesh recoloring Liang Wan, Yi Xiao. Ning Dou, Chi-Sing Leung, Yu-Kun Lai Multimedia Tools and Applications, vol. 77(11), 13753-13771, 2018. [paper] [doi]
		Mesh-based Autoencoders for Localized Deformation Component Analysis Qingyang Tan, Lin Gao, Yu-Kun Lai, Jie Yang, Shihong Xia AAAI Conference on Artificial Intelligence (spotlight), 2018 [paper] [official version] [code]
		Retrieving and Classifying Affective Images via Deep Metric Learning Jufeng Yang, Dongyu She, Yu-Kun Lai, Ming-Hsuan Yang AAAI Conference on Artificial Intelligence (oral), 2018 [paper] [official version]
		SF-Net: Learning Scene Flow from RGB-D Images with CNNs Yi-Ling Qiao, Lin Gao, Yu-Kun Lai, Fang-Lue Zhang, Ming-Ze Yuan, Shihong Xia British Machine Vision Conference (BMVC), 2018 [paper] [official version]
		Evaluation on the Compactness of Supervoxels Ran Yi, Yong-Jin Liu, Yu-Kun Lai IEEE International Conference on Image Processing, 2018 [paper] [doi]
		CFD: a collaborative feature difference method for spontaneous micro-expression spotting Yiheng Han, Bingjun Li, Yu-Kun Lai, Yong-Jin Liu IEEE International Conference on Image Processing, 2018 [paper] [doi]

2017

		Example-based image colorization using locality consistent sparse representation Bo Li, Fuchen Zhao, Zhuo Su, Xiangguo Liang, Yu-Kun Lai, Paul L. Rosin IEEE Transactions on Image Processing, vol. 26(11), 5188-5202, 2017 [paper] [doi]
		SPA: Sparse Photorealistic Animation Using a Single RGB-D Camera Kun Li, Jingyu Yang, Leijie Liu, Ronan Boulic, Yu-Kun Lai, Yebin Liu, Yubin Li, Eray Molla IEEE Transactions on Circuits and Systems for Video Technology, vol. 27(4): 771-783, 2017 [paper] [doi]
		Example-based image colorization via automatic feature selection and fusion Bo Li, Yu-Kun Lai, Paul L. Rosin Neurocomputing, vol. 266, 687-698, 2017 [paper] [doi]
		Data-Driven Shape Interpolation and Morphing Editing Lin Gao, Shu-Yu Chen, Yu-Kun Lai, Shihong Xia Computer Graphics Forum, vol. 36(8), pp. 19-31, 2017. [paper] [doi]
		Rigidity Controllable As-Rigid-As-Possible Shape Deformation Shu-Yu Chen, Lin Gao, Yu-Kun Lai, Shihong Xia Graphical Models, vol. 91: 13-27, 2017 [paper] [doi]
		Superlensing Microscope Objective Lens Bing Yan, Zengbo Wang, Alan L. Parker, Yu-Kun Lai, P. John Thomas, Liyang Yue, James N. Monks Applied Optics, vol. 56(11), pp. 3142-3147, 2017 [paper] [doi]
		A survey on human performance capture and animation Shihong Xia, Lin Gao, Yu-Kun Lai, Ming-Ze Yuan, Jinxiang Chai Journal of Computer Science and Technology, vol. 32(3), 536-554, 2017 [paper] [doi]
		Learning to Rank Retargeted Images Yang Chen, Yong-Jin Liu, Yu-Kun Lai IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 [paper] [doi]  [code]
		3-D Motion Recovery via Low Rank Matrix Restoration on Articulation Graphs Kun Li, Meiyuan Wang, Yu-Kun Lai, Jingyu Yang, Feng Wu IEEE International Conference on Multimedia and Expo (ICME), 2017 [paper] [doi]
		Global alignment for deformable objects captured by a single RGB-D camera Daoliang Guo, Kun Li, Yu-Kun Lai, Jingyu Yang IEEE International Conference on Multimedia and Expo (ICME), 2017 [paper] [doi]
		Transforming photos to comics using convolutional neural networks Yang Chen, Yu-Kun Lai, Yong-Jin Liu IEEE International Conference on Image Processing (ICIP), 2017 [paper]
		Depth-aware neural style transfer Xiao-Chang Liu, Ming-Ming Cheng, Yu-Kun Lai, Paul L. Rosin Symposium on Non-Photorealistic Animation and Rendering (NPAR), 2017 [paper] [doi]
		Benchmarking non-photorealistic rendering of portraits Paul L. Rosin, David Mould, Itamar Berger, John Collomosse, Yu-Kun Lai, Chuan Li, Hua Li, Ariel Shamir, Michael Wand, Tinghuai Wang, Holger Winnemöller Symposium on Non-Photorealistic Animation and Rendering (NPAR), 2017 [paper] [doi] [dataset]
		Watercolour Rendering of Portraits Paul L. Rosin, Yu-Kun Lai PSIVT Workshop on Vision meets Graphics, 2017 [paper]

2016

		Efficient and Flexible Deformation Representation for Data-Driven Surface Modeling Lin Gao, Yu-Kun Lai, Dun Liang, Shu-Yu Chen, Shihong Xia ACM Transactions on Graphics, vol. 35(5), pp.158:1-17, 2016 [paper] [doi] [video] [cover]
		Fast Capture of Textured Full-Body Avatar with RGB-D Cameras Shuai Lin, Yin Chen, Yu-Kun Lai, Ralph R. Martin, Zhi-Quan Cheng The Visual Computer, vol. 32(6-8), pp. 681-691, 2016 [paper] [doi]
		Color-aware surface registration Shuai Lin, Yu-Kun Lai, Ralph R. Martin, Shiyao Jin, Zhi-Quan Cheng Computers & Graphics, vol. 58, pp. 31-42, 2016 [paper] [doi]
		Semantic retrieval of trademarks based on conceptual similarity Fatahiyah Mohd Anuar, Rossitza Setchi, Yu-Kun Lai IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 46(2), pp. 220-233, 2016 [paper] [doi]
		Saliency guided local and global descriptors for effective action recognition Ashwan Abdulmunem, Yu-Kun Lai, Xianfang Sun Computational Visual Media, vol. 2(1), pp. 97-106, 2016 [paper] [doi]
		3D GLOH features for human action recognition Ashwan Abdulmunem, Yu-Kun Lai, Xianfang Sun International Conference on Pattern Recognition (ICPR), 2016 [paper] [doi]
		3-D motion recovery via low rank matrix analysis Meiyuan Wang, Kun Li, Feng Wu, Yu-Kun Lai, Jingyu Yang IEEE International Conference on Visual Communications and Image Processing (VCIP), 2016 [paper] [doi]
		Recovering historical film footage by processing microtomographic images Chang Liu, Paul L. Rosin, Yu-Kun Lai, Graham R. Davis, David Mills, Charles Norton World Cultural Heritage Conference, 2016 [paper] [doi]

2015

		Active Exploration of Large 3D Model Repositories Lin Gao, Yan-Pei Cao, Yu-Kun Lai, Hao-Zhi Huang, Leif Kobbelt, Shi-Min Hu IEEE Transactions on Visualization and Computer Graphics, vol. 21(12), pp. 1390-1402, 2015 [paper] [doi] [video]
		Optimization-based gradient mesh colour transfer Yi Xiao, Liang Wan, Chi Sing Leung, Yu-Kun Lai, Tien-Tsin Wong Computer Graphics Forum, vol. 34(6), pp. 123-134, 2015 [paper] [doi]
		Sparse non-rigid registration of 3D shapes Jingyu Yang, Ke Li, Kun Li, Yu-Kun Lai Computer Graphics Forum, vol. 34(5), pp. 89-99, 2015 [paper] [doi]
		3D indoor scene modeling from RGB-D data: a survey Kang Chen, Yu-Kun Lai, Shi-Min Hu Computational Visual Media, vol. 1(4), pp. 267-278, 2015 [paper] [doi]
		Non-photorealistic rendering of portraits Paul L. Rosin, Yu-Kun Lai Proc. Computational Aesthetics, 2015 [paper] [doi]
		Robust segmentation of historical parchment XMT images for virtual unrolling Chang Liu, Paul L. Rosin, Yu-Kun Lai, Weiduo Hu Proc. Digital Heritage, 2015 [paper] [doi]

2014

		Automatic Semantic Modeling of Indoor Scenes from Low-quality RGB-D Data using Contextual Information Kang Chen, Yu-Kun Lai, Yu-Xin Wu, Ralph R. Martin, Shi-Min Hu ACM Transactions on Graphics (ACM SIGGRAPH Asia), vol. 33(6), 208:1-12, 2014 [paper] [doi] [project]
		BiggerPicture: Data-driven Image Extrapolation Using Graph Matching Miao Wang, Yu-Kun Lai, Yuan Liang, Ralph R. Martin, Shi-Min Hu ACM Transactions on Graphics (ACM SIGGRAPH Asia), vol. 33(6), 173:1-13, 2014 [paper] [doi] [project]
		Diffusion Pruning for Rapidly and Robustly Selecting Global Correspondences using Local Isometry Gary K.L. Tam, Ralph R. Martin, Paul L. Rosin, Yu-Kun Lai ACM Transactions on Graphics, vol. 33(1), Article No. 4, pp. 1-17, 2014 [paper] [doi] [cover] [executable] [request MATLAB code]
		Parametric Meta-Filter Modeling from a Single Example Pair Shi-Sheng Huang, Guo-Xin Zhang, Yu-Kun Lai, Johannes Kopf, Daniel Cohen-Or, Shi-Min Hu The Visual Computer, vol. 30(6-8), pp. 673--684, 2014 [paper] [doi] [project]
		Efficient Circular Thresholding Yu-Kun Lai, Paul L. Rosin IEEE Transactions on Image Processing, vol. 23(3), pp. 992-1001, 2014 [paper] [doi] [code]
		Virtual unrolling and information recovery from scanned historical documents Oksana Samko, Yu-Kun Lai, David Marshall, Paul L. Rosin Pattern Recognition, vol. 47(1), pp. 248-259, 2014 [paper] [doi]
		Artistic rendering enhancing global structure Yu-Kun Lai, Paul L. Rosin The Visual Computer, vol. 30(10), pp. 1179-1193, 2014 [paper] [doi]
		Use of non-photorealistic rendering and photometric stereo in making bas-reliefs from photographs Jing Wu, Ralph R. Martin, Paul L. Rosin, Xianfang Sun, Yu-Kun Lai, Yonghuai Liu, Christian Wallraven Graphical Models, vol. 76(4), pp. 202-213, 2014 [paper] [doi]
		An Efficient Approach to Correspondences between Multiple Non-Rigid Parts Gary K.L. Tam, Ralph R. Martin, Paul L. Rosin, Yu-Kun Lai Computer Graphics Forum vol. 33(5), pp. 137-146, 2014 [paper] [doi]
		Apocalypto: revealing the Bressingham roll David Mills, Antoinette Curtis, Graham Davis, Paul L. Rosin, Yu-Kun Lai Journal of Paper Conservation, vol. 15(3), pp. 14-19, 2014 [paper]

2013

		A Data-Driven Approach to Realistic Shape Morphing Lin Gao, Yu-Kun Lai, Qixing Huang and Shi-Min Hu Computer Graphics Forum (Eurographics), vol. 32(2), 449-457, 2013 [paper] [doi] [video]
		Generalized Anisotropic Stratified Surface Sampling Jon Quinn, Frank Langbein, Yu-Kun Lai, Ralph R. Martin IEEE Transactions on Visualization and Computer Graphics, vol. 19(7), 1143-1157, 2013 [paper] [doi]
		Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Non-Rigid Gary K.L. Tam, Zhi-Quan Cheng, Yu-Kun Lai, Frank Langbein, Yonghuai Liu, David Marshall, Ralph R. Martin, Xianfang Sun and Paul L. Rosin IEEE Transactions on Visualization and Computer Graphics, vol. 19(7), 1199-1217, 2013 [paper] [doi]
		Efficient Synthesis of Gradient Solid Textures Guo-Xin Zhang, Yu-Kun Lai, Shi-Min Hu Graphical Models, vol. 75(3), 104-117, 2013 (Preliminary version appears in Proc. Computational Visual Media 2012 and receives Best Paper Award) [paper] [doi]
		Example-based Color Transfer for Gradient Meshes Yi Xiao, Liang Wan, Chi-Sing Leung, Yu-Kun Lai, Tien-Tsin Wong IEEE Transactions on Multimedia, vol. 15(3), pp. 549-560, 2013 [paper] [doi]
		Artistic minimal rendering with lines and blocks Paul L. Rosin, Yu-Kun Lai Graphical Models, vol. 75(4), pp. 208-229, 2013 [paper] [doi]
		SuperMatching: feature matching using supersymmetric geometric constraints Zhi-Quan Cheng, Yin Chen, Ralph R. Martin, Yu-Kun Lai, Aiping Wang IEEE Transactions on Visualization and Computer Graphics, vol. 19(11), pp. 1885-1894, 2013. [paper] [doi]
		Making bas-reliefs from photographs of human faces Jing Wu, Ralph R. Martin, Paul L. Rosin, Xianfang Sun, Frank C. Langbein, Yu-Kun Lai, Dave Marshall, Yonghuai Liu Computer-Aided Design, vol. 45(3), pp. 671-682, 2013. [paper] [doi]
		Non-photorealistic rendering with spot colour Paul L. Rosin, Yu-Kun Lai Proceedings of Computational Aesthetics, pp. 67-76, 2013. [paper] [doi]
		Non-photorealistic rendering with reduced colour palettes Yu-Kun Lai, Paul L. Rosin Image and Video-based Artistic Stylisation, Computational Imaging and Vision series, vol. 42(2), pp. 211-236, Springer, 2013. [paper] [doi]

2012

		Improved Initialisation for Centroidal Voronoi Tessellation and Optimal Delaunay Triangulation Jonathan A. Quinn, Feng Sun, Frank C. Langbein, Yu-Kun Lai, Wenping Wang and Ralph R. Martin Computer-Aided Design, vol. 44(11), pp. 1062-1071, 2012 [paper] [doi]
		Vertex Location Optimisation for Improved Remeshing Yu-Kun Lai, Ralph R. Martin Graphical Models, vol. 74(4), pp. 233-243, 2012 [paper] [doi]
		Lp Shape Deformation Lin Gao, Guo-Xin Zhang, Yu-Kun Lai Science China Information Sciences, vol. 55(5), pp. 983-993, 2012 [paper] [doi]

2011

Sketch Guided Solid Texturing Guo-Xin Zhang, Song-Pei Du, Yu-Kun Lai, Tianyun Ni, Shi-Min Hu Graphical Models, vol. 73(3), pp. 59-73, 2011 [paper] [doi]

2010

		Metric Driven RoSy Field Design and Remeshing Yu-Kun Lai, Miao Jin, Xuexiang Xie, Ying He, Jonathan Palacios, Eugene Zhang, Shi-Min Hu, Xianfeng David Gu IEEE Transactions on Visualization and Computer Graphics, vol. 16(1), pp. 95-108, 2010 [paper] [doi]
		Feature Aligned Quad Dominant Remeshing using Iterative Local Updates Yu-Kun Lai, Leif Kobbelt, Shi-Min Hu Computer-Aided Design, vol. 42(2), pp. 109-117, 2010 (Preliminary version appears in Proc. ACM Solid and Physical Modeling 2008.) [paper] [doi]
		Towards Artistic Minimal Rendering Paul L. Rosin, Yu-Kun Lai ACM Symposium on Non Photorealistic Rendering (NPAR), pp. 119-127, 2010 [paper] [doi] [online demo]
		Harmonic Field Based Volume Model Construction from Triangle Soup Chao-Hui Shen, Guo-Xin Zhang, Yu-Kun Lai, Shi-Min Hu, R. R. Martin Journal of Computer Science and Technology, vol. 25(3), pp. 562-571, 2010 [paper] [doi]

2009

		Automatic and Topology Preserving Gradient Mesh Generation for Image Vectorization Yu-Kun Lai, Shi-Min Hu, Ralph R. Martin ACM Transactions on Graphics (ACM SIGGRAPH), vol. 28(3), Article No. 85 [paper] [doi]
		Rapid and Effective Segmentation of 3D Models using Random Walks Yu-Kun Lai, Shi-Min Hu, Ralph R. Martin Computer Aided Geometric Design, vol. 26(6), pp. 665-679, 2009 (Preliminary version appears in Proc. ACM Solid and Physical Modeling 2008). [paper] [doi] [code request]
		Stripification of Free-Form Surfaces with Global Error Bounds for Developable Approximation Yon-Jin Liu, Yu-Kun Lai, Shi-Min Hu IEEE Transactions on Automation Science and Engineering, vol. 6(4), pp. 700-709, 2009 [paper] [doi] [video] [code]
		Robust Principal Curvatures using Feature Adapted Integral Invariants Yu-Kun Lai, Shi-Min Hu, Fang Tong SIAM/ACM Joint Conference on Geometric and Physical Modeling, pp. 325-330, 2009 [paper] [doi]

2008

		Fairing Wireframes in Industrial Surface Design Yu-Kun Lai, Yong-Jin Liu, Yu Zang, Shi-Min Hu IEEE International Conference on Shape Modeling and Applications (SMI), pp. 29-35, 2008 [paper] [doi]
		Note on Industrial Applications of Hu's Surface Extension Algorithm Zang Yu, Yong-Jin and, Yu-Kun Lai Geometric Modeling Processing, pp. 304-314, 2008 [paper] [doi]

2007

		Robust Feature Classification and Editing Yu-Kun Lai, Qian-Yi Zhou, Shi-Min Hu, Johannes Wallner, Helmut Pottmann IEEE Transactions on Visualization and Computer Graphics, vol. 13, Jan/Feb, pp. 34-45, 2007 [paper] [doi]
		Principal curvatures from the integral invariant viewpoint Helmut Pottmann, Johannes Wallner, Yong-Liang Yang, Yu-Kun Lai, Shi-Min Hu Computer Aided Geometric Design, vol. 24, pp. 428-442, 2007 [paper] [doi]

2006

		Surface Fitting Based on a Feature Sensitive Parameterization Yu-Kun Lai, Shi-Min Hu, Helmut Pottmann Computer-Aided Design, Vol. 38, No. 7, pp. 800-807, 2006 [paper] [doi]
		Surface Mosaics Yu-Kun Lai, Shi-Min Hu, Ralph R. Martin The Visual Computer (Pacific Graphics), vol. 22, no. 9-11, pp. 604-611, 2006 [paper] [doi]
		Feature Sensitive Mesh Segmentation Yu-Kun Lai, Shi-Min Hu, Ralph R. Martin ACM Symposium on Solid and Physical Modeling, pp. 7-16, 2006 [paper] [doi]
		Robust Principal Curvatures on Multiple Scales Yong-Liang Yang, Yu-Kun Lai, Shi-Min Hu, Helmut Pottmann Eurographics Symposium on Geometry Processing, pp. 223-226, 2006 [paper] [doi]

2005

Geometric texture synthesis and transfer via geometry images Yu-Kun Lai, Shi-Min Hu, Xianfeng Gu, Ralph R. Martin ACM Symposium on Solid and Physical Modeling, pp. 15-26, 2005 [paper] [doi]

Prizes and Honours         Top

• National Excellent Doctoral Dissertation of China Award, 2010.
• Excellent PhD Graduate, Dept. of Computer Science and Technology, Tsinghua University, 2008.
• First-Class Excellent Doctoral Thesis, Tsinghua University, 2008.
• Microsoft Fellowship, 2007.
• First-Class Scholarship of Excellent Students in Tsinghua Univ. (Morgan Stanley Scholarship), 2006.
• Excellet Graduate of Tsinghua University, 2003.
• Excellent Bachelor Thesis, Tsinghua University, 2003.
  
• First-Class Scholarship of Excellent Students in Tsinghua Univ. (Sony Scholarship), 2002.
• Gold Medal in National Olympiad in Informatics (NOI) of China, 1998.

Education   Top

Visiting Experience Top

10/2007-04/2008        Center for Visual Computing, State University of New York at Stony Brook, Stony Brook, NY 11790, USA.