教育背景

博士(香港大学)

理学硕士(浙江大学)

理学学士(南京航空航天大学)

研究领域

计算机视觉;计算机图形学;人机交互;医学图像处理;机器学习

个人简介

韩晓光博士,现任香港中文大学(深圳)理工学院和未来智联网络研究院助理教授,校长青年学者,目前担任未来智联网络研究院助理院长。他于2017年获得香港大学计算机科学专业博士学位。其研究方向包括计算机视觉和计算机图形学等,在该方向著名国际期刊和会议已发表论文60余篇,包括顶级会议和期刊SIGGRAPH(Asia), CVPR, ICCV, ECCV, NeurIPS, ACM TOG, IEEE TPAMI等。他曾获得吴文俊人工智能优秀青年奖,广东省杰出青年基金资助,香港中文大学(深圳)青年科研奖。目前也担任CVPR2023,NeurIPS 2023以及CVPR2024领域主席。他的工作还曾两次获得CCF图形开源数据集奖(DeepFashion3D和MVImgNet),2019年和2020年连续两年入选计算机视觉顶级会议CVPR最佳论文列表(入选率分别为0.8%和0.4%),他也曾获得IEEE TVCG最佳审稿人提名奖。

* Joint first authors     # Corresponding author

[1] Kun Zhou, Xiaoguang Han, Nianjuan Jiang, Kui Jia, and Jiangbo Lu, HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2021.

[2] Yuda Qiu, Xiaojie Xu, Lingteng Qiu, Yan Pan, Yushuang Wu, Weikai Chen, Xiaoguang Han#, 3DCaricShop: A Dataset and A Baseline Method for Single-view 3D Caricature Face Reconstruction. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021.

[3] Yinyu Nie, Ji Hou, Xiaoguang Han#, Matthias Nieβner, RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021.

[4] Haolin Liu, Anran Lin, Xiaoguang Han#, Lei Yang, Yizhou Yu, Shuguang Cui, Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021.

[5] Yinyu Nie, Yiqun Lin, Xiaoguang Han#, Shihui Guo, Jian Chang, Shuguang Cui, Jianjun Zhang, Skeleton-bridged Point Completion: From Global Inference to Local Adjustment. NeuIPS 2020.

[6] Heming Zhu*, Yu Cao*, Hang Jin*, Weikai Chen, Dong Du, Zhangye Wang, Shuguang Cui, Xiaoguang Han#, Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images. ECCV 2020 (Oral, 2%).

[7] Lingteng Qiu, Xuanye Zhang, Yanran Li, Guanbin Li, Xiaojun Wu, Zixiang Xiong, Xiaoguang Han#, Shuguang Cui, Peeking into occluded joints: A novel framework for crowd pose estimation. ECCV 2020.

[8] Yinyu Nie, Xiaoguang Han#, Shihui Guo, Yujian Zheng, Jian Chang, Jianjun Zhang, Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction forIndoor Scenes from a Single Image. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020 (Oral, Paper Award Nominees, ~0.4%).

[9] Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han#. FPConv: Learning Local Flattening for Point Convolution. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020.

[10] Xiaojun Jia, Xingxing Wei, Xiaochun Cao, Xiaoguang Han, Adv-watermark: A Novel Watermark Perturbation for Adversarial Examples. ACM MM 2020.

[11] Xianggang Yu, Haolin Liu, Xiaoguang Han#, Zhen Li, Zixiang Xiong, Shuguang Cui, JAFPro: Joint Appearance Fusion and Propagation for Human Video Motion Transfer from Multiple Reference Images. ACM MM 2020.

[12] Jie Wu, Guanbin Li, Xiaoguang Han, Liang Lin, Reinforcement Learning for Weakly Supervised Temporal Grounding of Natural Language in Untrimmed Videos. ACM MM 2020.

[13] Dong Du, Xiaoguang Han#, Hongbo Fu, Feiyang Wu, Yizhou Yu, Shuguang Cui, Ligang Liu, SAniHead: Sketching Animal-like 3D Character Heads Using a View-surface Collaborative Mesh Generative Network. IEEE TVCG 2020.

[14] Chaowei Fang, Guanbin Li, Xiaoguang Han, Yizhou Yu. Self-Enhanced Convolutional Network for Facial Video Hallucination. IEEE Transactions on Image Processing (IEEE TIP) 2020.

[15] Jinmiao Cai, Nianjuan Jiang, Xiaoguang Han, Kui Jia, Jiangbo Lv, JOLO-GCN: Mining Joint-Centered Light-Weight Information for Skeleton-Based Action Recognition. WACV 2020.

[16] Dong Du, Heming Zhu, Yinyu Nie, Xiaoguang Han#, Shuguang Cui, Yizhou Yu, Ligang Liu, Learning Part Generation and Assembly for Sketching Man-made Objects. Pacific Graphics 2020.

[17] Yao Li, Xianggang Yu, Xiaoguang Han#, Nianjuan Jiang, Kui Jia, Jiangbo Lv, A Deep Learning Based Interactive Sketching System for Fashion Images Design. Pacific Graphics 2020.

[18] Xiangyu Zhu, Xiaoguang Han#, Wei Zhang, Jian Zhao, Ligang Liu. Learning intrinsic decomposition of complex-textured fashion images. IEEE International Conference on Multimedia & Expo (ICME) 2020.

[19] Dong Du, Zhiyi Zhang, Xiaoguang Han#, Shuguang Cui, Ligang Liu, VIPNet: a fast and accurate single-view Volumetric reconstruction by learning sparse Implicit Point guidance. 3DV 2020.

[20] Kun Zhou, Xiaoguang Han, Nianjuan Jiang, Kui Jia, Jiangbo Lv. HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation. IEEE International Conference on Computer Vision (ICCV) 2019.

[21] Junyi Pan, Xiaoguang Han, Weikai Chen, Jiapeng Tang, Kui Jia. Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks. IEEE International Conference on Computer Vision (ICCV) 2019.

[22] Xiaoguang Han, Zhaoxuan Zhang, Dong Du, Mingdai Yang, Jingming Yu, Pan Pan, Xin Yang, Ligang Liu, Zixiang Xiong, Shuguang Cui. Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019 (Oral, ~5.6%).

[23] Jiapeng Tang*, Xiaoguang Han*, Junyi Pan, Kui Jia, Xin Tong. A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Images. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019 (Oral, Best Paper Finalist, ~ 0.8%).

[24] Chuan Wang, Haibin Huang, Xiaoguang Han#, Jue Wang. Video Inpainting by Jointly Learning Temporal Structure and Spatial Details. The 33rd AAAI Conference on Artificial Intelligence (AAAI) 2019.

[25] Haonan Qiu, Chuan Wang, Hang Zhu, Xiangyu Zhu, Jinjin Gu, Xiaoguang Han#, Two-phase Hair Image Synthesis by Self-Enhancing Generative Model. Journal of Computer Graphics Forum (Pacific Graphics) 2019.

[26] Zizheng Yan, Xiaoguang Han#, Changmiao Wang, Yuda Qiu, Zixiang Xiong, Shuguang Cui. Learning mutually local-global u-nets for high-resolution retinal lesion segmentation in fundus images. IEEE International Symposium on Biomedical Imaging (IEEE ISBI) 2019.

[27] Yanlong Tang, Xiaoguang Han#, Yue Li, Ruofeng Tong. Expressive facial style transfer for personalized memes mimic. Proceeding of CGI 2019. (The visual computer)

[28] Xiaoguang Han, Kangcheng Hou, Dong Du, Yuda Qiu, Shuguang Cui, Kun Zhou, Yizhou Yu. CaricatureShop: Personalized and Photorealistic Caricature Sketching. IEEE Transactions on Visualization and Computer Graphics (TVCG) 2018.

[29] Xiaoguang Han*, Zhen Li*, Haibin Huang, Evangelos Kalogerakis, Yizhou Yu. High Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference. IEEE International Conference on Computer Vision (ICCV) 2017 (Spotlight Oral, ~5%).

[30] Xiaoguang Han, Chang Gao, Yizhou Yu. DeepSketch2Face: A Deep Learning Based Sketching System for 3D Face and Caricature Modeling. ACM Transaction on Graphics (TOG), Proceedings of ACM SIGGRAPH 2017. Part of the Technical Papers Video Trailer, a featured talk invited by NVIDIA.

[31] Xiaoguang Han, Hongchuan Yu, Yizhou Yu, Jianjun Zhang, A fast propagation scheme for approximate geodesic paths, CVM 2017, Journal of Graphical Models.

[32] Yipeng Qin*, Xiaoguang Han*, Hongchuan Yu, Yizhou Yu, Jianjun Zhang. Fast and Exact Discrete Geodesic Computation Based on Triangle-Oriented Wavefront Propagation. ACM Transaction on Graphics (TOG), Proceedings of ACM SIGGRAPH 2016.

[33] Xiaoguang Han, Kenneth K.Y. Wong, Yizhou Yu. 3D Human Model Reconstruction from Sparse Uncalibrated Views. IEEE Computer Graphics and Applications (IEEE CG&A) 2016. One of the Notable Articles of the 21st Annual Best of Computing.

[34] Sai Bi, Xiaoguang Han, Yizhou Yu. An L1 Image Transform for Edge-Preserving Smoothing and Scene-Level Intrinsic Decomposition. ACM Transaction on Graphics (TOG), Proceedings of ACM SIGGRAPH 2015.

[35] Hongbo Fu, Xiaoguang Han, Quoc Huy Phan. Data-driven Suggestions for Portrait Posing. SIGGRAPH ASIA 2013 Technical Briefs and Emerging Technologies. Best Demo AwardOne of the four program highlights.

[36] Xiaoguang Han, Hongbo Fu, Hanlin Zheng, Ligang Liu, Jue Wang. A Video-based Interface for Hand-Driven Stop Motion Animation Production. IEEE Computer Graphics and Applications (IEEE CG&A) 2013.

[37] Shizhe Zhou, Hongbo Fu, Ligang Liu, Daniel Cohen-Or, Xiaoguang Han. Parametric Reshaping of Human Bodies in Images. ACM Transaction on Graphics (TOG), special issue: Proceedings of ACM SIGGRAPH 2010. One of the six highlights among all SIGGRAPH 2010 papers.