徐士彪(Shibiao Xu) [English],副研究员,硕士生导师,中国科学院自动化研究所
电子邮件: shibiao DOT xu AT nlpr DOT ia DOT ac DOT cn
办公电话: 010-82544702
通信地址: 北京市海淀区中关村东路95号(100190),智能化大厦1309室

个人介绍

现任岗位为中国科学院自动化研究所,模式识别国家重点实验室, 三维可视计算团队的副研究员(硕士生导师)。目前主要研究方向集中在三维计算机视觉、模式识别、深度学习、遥感图像处理及虚拟现实等领域,具体包括计算机视觉中的场景目标识别与分类、视觉重建、物体分割等,计算机图形学中的虚实场景融合及可视化等,以及机器学习中的概率图模型和深度学习等。在相关领域学术会议和期刊上共发表论文40余篇,主要包括JCR I 区顶级SCI国际期刊IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI),IEEE Trans. on Geoscience and Remote Sensing,IEEE Trans. on Image Processing (TIP), IEEE Trans. on Neural Networks and Learning Systems(TNNLS),IEEE Trans. on Visualization and Computer Graphics (TVCG)Pattern Recognition (PR)和Information Fusion共计12篇,计算机视觉、计算机图形学及机器人领域顶级国际会议IEEE Conference on Computer Vision and Pattern Recognition(CVPR), IEEE International Conference on Computer Vision(ICCV),IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS),ACM International Conference on Multimedia(MM),ACM SIGGRAPH Asia 和ACM SIGGRAPH共计8篇,领域知名SCI期刊10篇,授权发明专利6项,所提出的三维复杂场景信息获取与理解方法作为核心工作,获得2017年度陕西高等学校科学技术奖一等奖。主持国家自然科学基金面上项目及子项目5项,同时作为实际负责人,承担国家自然科学基金重点项目、重大研究计划重点项目及国家863项目子项目等4项,项目总经费达1000万以上。

2009年6月,本科毕业于北京邮电大学信息工程专业;2014年6月,博士毕业于中国科学院自动化研究所计算机应用专业,导师张晓鹏研究员(三维可视计算团队负责人)。2014年7月至2016年4月,在北京航空航天大学虚拟现实技术与系统国家重点实验室,从事博士后研究工作,合作导师沈旭昆教授。


最新消息:

2021年1月Retinal Vessel Segmentation via Context Guide Attention Net with Joint Hard Sample Mining Strategy (通信作者)论文国际会议IEEE International Symposium on Biomedical Imaging (ISBI) 2021接收

A Periodic Frame Learning Approach for Accurate Landmark Localization in M-mode Echocardiography
(第二作者)
论文
国际会议IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2021接收

2020年11月~12月Real-Time Orthophoto Mosaicing on Mobile Devices for Sequential Aerial Images with Low Overlap (通信作者)论文SCI国际期刊Remote Sensing接收

A Hybrid Convolutional Architecture for Accurate Image Manipulation Localization at the Pixel-Level (通信作者)论文SCI国际期刊Multimedia Tools and Applications接收

2020年10月Multi-view Feature Aggregation for Facade Parsing (第二作者)论文SCI国际期刊IEEE Geoscience and Remote Sensing Letters接收

2020年9月Accurate Rock-mass Extraction from Terrestrial Laser Point Clouds via Multi-scale and Multi-view Convolutional Feature Representation (第二作者)论文顶级国际期刊IEEE Trans. on Geoscience and Remote Sensing接收

MLIFeat: Multi-level information fusion based deep local features (通信作者)论文被计算机视觉国际会议Asian Conference on Computer Vision (ACCV) 2020接收

2020年8月Multi-scale Spatial Context-Based Semantic Edge Detection (通信作者)论文被顶级国际期刊Information Fusion接收

2020年7月Efficient Joint Gradient Based Attack Against SOR Defense for 3D Point Cloud Classification (通信作者)论文被顶级国际会议ACM International Conference on Multimedia 2020接收

2020年7月Fast Georeferenced Aerial Image Stitching with Absolute Rotation Averaging and Planar Restricted Pose Graph (通信作者)论文被顶级国际期刊IEEE Trans. on Geoscience and Remote Sensing接收。

2020年6月KGSNet: Key-Point-Guided Super-Resolution Network for Pedestrian Detection in the Wild (通信作者)论文被顶级国际期刊IEEE Trans. on Neural Networks and Learning Systems接收。

2020年6月DenseFusion: Large-Scale Online Dense Pointcloud and DSM Mapping for UAVs (通信作者)论文被顶级国际会议IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020接收

2020年1月~5月Unsupervised Multi-view Constrained Convolutional Network for Accurate Depth Estimation (共同第一作者,通信作者)论文被顶级国际期刊IEEE Trans. on Image Processing接收

3篇论文分别被SCI国际期刊MTA,IET CV和GRSL接收。

2019年7月GSLAM: A General SLAM Framework and Benchmark (共同第一作者,通信作者)论文被顶级国际会议ICCV接收。

2019年6月Learning Graph Structure via Graph Convolutional Networks论文被顶级国际期刊Pattern Recognition接收。

招生情况

常年招收全日制保研及考研学生!


招生专业:

081203-计算机应用技术
081104-模式识别与智能系统


招生方向:

计算机视觉、模式识别、深度学习、遥感图像处理、虚拟现实

项目经历

1.国家自然科学基金面上项目,61971418,基于多视角卷积网络的稠密SLAM场景重建与识别, 2020.01至2023.12,负责人;
2.国家自然科学基金面上项目,61671451,基于多视角航拍图像的大规模城市场景快速重建, 2017.01至2020.12,负责人;
3.国家自然科学基金国际(地区)合作与交流重点项目,61620106003,联合的图像大数据语义分析与城市场景重建, 2017.01至2021.12,第二实际负责人;
4.国家自然科学基金大数据驱动的管理与决策研究重大研究计划项目,91646207,城市道路交通大数据融合方法研究, 2017.01至2021.12,第一实际负责人
5.国家自然科学基金面上项目子项目,61571400,基于株型参数虚拟量测及过程模型参数智能提取的植物三维重建方法, 2016.01至2019.12,负责人;
6.国家自然科学基金面上项目子项目,61571046,图像块结构提取与分析及其在图像分类中的应用, 2016.01至2019.12,负责人;
7.国家自然科学基金面上项目子项目,61771026,基于多视点图像序列三维场景稀疏结构与语义重建, 2018.01至2021.12,负责人。

发表论文

       
Unsupervised Multi-view Constrained Convolutional Network for Accurate Depth Estimation 
Yuyang Zhang, Shibiao Xu, Baoyuan Wu, Jian Shi , Weiliang Meng and Xiaopeng Zhang                      
IEEE Transactions on Image Processing (TIP): 2020                
[Project page] [DOI]

       
GSLAM: A General SLAM Framework and Benchmark                        
Yong Zhao, Shibiao Xu, Shuhui Bu, Hongkai Jiang and Pengcheng Han                
IEEE International Conference on Computer Vision (ICCV): 2019                
[Project page] [DOI]

       
Learning Graph Structure via Graph Convolutional Networks                        
Qi Zhang, Jianlong Chang, Gaofeng Meng, Shibiao Xu, Chunhong Pan and Shiming Xiang                
Pattern Recognition: 2019                
[Project page] [DOI]

       
Realistic Procedural Plant Modeling from Multiple View Images                        
Jianwei Guo, Shibiao Xu, Dong-Ming Yan, Zhanglin Cheng, Marc Jaeger and Xiaopeng Zhang
IEEE Transactions on Visualization and Computer Graphics (TVCG): 2018 
[Project page] [DOI]

       
Nonlinear Asymmetric Multi-Valued Hashing                        
Cheng Da, Gaofeng Meng, Shiming Xiang, Kun Ding, Shibiao Xu, Qing Yang and Chunhong Pan 
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI): 2018    
[Project page] [DOI]

       
Automatic Building Rooftop Extraction from Aerial Images via Hierarchical RGB-D Priors
Shibiao Xu, Xingjia Pan, Er Li, Baoyuan Wu, Shuhui Bu,  Weiming Dong, Shiming Xiang and  Xiaopeng Zhang
IEEE Transactions on Geoscience and Remote Sensing (TGRS):2018        
[Project page] [DOI]

       
PM-PM: PatchMatch With Potts Model for Object Segmentation and Stereo Matching                        
Shibiao Xu, Feihu Zhang, Xiaofei He,  Xukun Shen and  Xiaopeng Zhang                   
IEEE Transactions on Image Processing (TIP): 2015 ,24(7):2182-2196                
[Project page] [DOI]

       
Automatic Road Detection and Centerline Extraction via Cascaded End-to-end Convolutional Neural Network 
Guangliang Cheng, Ying Wang,  Shibiao Xu (Corresponding author), Hongzhen Wang,  Shiming Xiang and  Chunhong Pan 
IEEE Transactions on Geoscience and Remote Sensing (TGRS): 2017, 55(6):3322-3337                
[Project page] [DOI]

       
Building Extraction from Remotely Sensed Images by Integrating Saliency Cue 
Er Li, Shibiao Xu (Joint first author),  Weiliang Meng and Xiaopeng Zhang              
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARs): 2017, 10(3):906-919                
[Project page] [DOI]

       
Robust Rooftop Extraction from Visible Band Images Using Higher Order CRF 
Er Li, John Femiani, Shibiao Xu,  Xiaopeng Zhang and Peter Wonka              
IEEE Transactions on Geoscience and Remote Sensing (TGRS): 2015, 53(8):4483-4495                
[Project page] [Code coming soon] [DOI]

       
AMVH: Asymmetric Multi-Valued Hashing                        
Cheng Da, Shibiao Xu,  Kun Ding, Gaofeng Meng and Shiming Xiang              
IEEE Conference on Computer Vision and Pattern Recognition (CVPR): 2017, 898-906                
[Project page] [DOI]

       
High accuracy correspondence field estimation via MST based patch matching
Feihu Zhang, Shibiao Xu (Corresponding author) and  Xiaopeng Zhang (Corresponding author) 
Multimedia Tools and Applications: 2020
       
Pyramid ALKNet for Semantic Parsing of Building Facade Image                        
Wenguang Ma, Wei Ma, Shibiao Xu and  Hongbin Zha              
Geoscience and Remote Sensing Letters: 2020
       
Learning across Views for Stereo Image Completion                        
Wei Ma, Mana Zheng, Wenguang Ma, Shibiao Xu (Corresponding author) and Xiaopeng Zhang 
IET Computer Vision: 2020
       
Real-time pedestrian detection via hierarchical convolutional feature                        
Dongming Yang, Jiguang Zhang, Shibiao Xu (Corresponding author), Shuiying Ge, G. Hemantha Kumar and Xiaopeng Zhang              
Multimedia Tools and Applications: 2018
       
Accurate Blind Deblurring Using SalientPatch-Based Prior for Large-Size Images
Chengcheng Ma, Jiguang Zhang, Shibiao Xu (Corresponding author), Weiliang Meng, Runping Xi, G. Hemantha Kumar and Xiaopeng Zhang              
Multimedia Tools and Applications: 2018
       
Interactive Stereo Image Segmentation via Adaptive Prior Selection                        
Wei Ma, Yue Qin, Shibiao Xu (Corresponding author) and Xiaopeng Zhang 
Multimedia Tools and Applications: 2018
       
Interactive Stereo Image Segmentation with RGB-D hybrid Constraints 
Wei Ma, Yue Qin, Luwei Yang, Shibiao Xu (Corresponding author) and Xiaopeng Zhang              
IEEE Signal Processing Letter: 2016 ,23(11):1533-1537
       
Real-time ink simulation using a grid-particle method                        
Shibiao Xu, Xing Mei, Weiming Dong, Zhiyi Zhang and Xiaopeng Zhang              
Computers & Graphics: 2012 ,36(8):1025-1035
       
Joint Depth Map Interpolation and Segmentation with Planar Surface Model 
Shibiao Xu, Longquan Dai, Jiguang Zhang, Jinhui Tang, G.Hemanth Kumar, Yanning Zhang and Xiaopeng Zhang              
Siggraph Asia Technical Briefs: 2016 ,22:1--22:4
       
Depth of Field Rendering via Adaptive Recursive Filtering                        
Shibiao Xu, Xing Mei, Weiming Dong, Xun Sun, Xukun Shen and Xiaopeng Zhang
Siggraph Asia Technical Briefs: 2014 ,18:1-18:4
       
Statistical Learning Based Facial Animation                        
Shibiao Xu, Guanghui Ma, Weiliang Meng and Xiaopeng Zhang              
Journal of Zhejiang University-SCIENCE C: 2013 ,14(7):542-550
       
Hybrid Tree Guided Patch Matching                        
Shibiao Xu, Jiguang Zhang, Weilong Ding,  Xukun Shen, G. Hemanth Kumar and Xiaopeng Zhang 
International Conference on Virtual Reality and Visualization: 2015 ,9-15
       
Interactive Visual Simulation of Dynamic Ink Diffusion Effects                        
Shibiao Xu, Xing Mei , Weiming Dong,  Zhiyi Zhang and Xiaopeng Zhang              
Virtual Reality Continuum and Its Applications: 2011 ,109-116
       
Realistic procedural plant modeling guided by 3D point cloud                        
Jianwei Guo, Zhanglin Cheng,  Shibiao Xu and Xiaopeng Zhang              
ACM Siggraph Posters: 2017
       
Compressive Sensing for Noisy Solder Joint Imagery Based on Convex Optimization 
Huihuang Zhao, Jianzhen Chen, Shibiao Xu, Ying Wang, Zhijun Qiao              
Soldering & Surface Mount Technology: 2016 ,28(2):114-122
       
Automatic Motion Generation Based on Path Editing from Motion Capture Data
Xiaoyue Guo, Shibiao Xu, Wujun Che and Xiaopeng Zhang              
Transactions on Edutainment: 2010 ,4:91-4:104

发明专利

1.徐士彪,梅星,董未名,张之益、张晓鹏. ZL201110398914.4,2014.02.05,三维水墨动画的制作方法,中国,已授权
2.张晓鹏,徐士彪,于海涛,沈文. ZL201210394304.1,2015.02.11,互动式生成液滴效果的方法,中国,已授权
3.代龙泉, 袁梦珂, 徐士彪,张晓鹏. ZL201610143582.8,2016.03.15,双边数字图像滤波器的加速方法和系统,中国,已授权
4.张晓鹏, 代龙泉, 袁梦轲, 张飞虎,徐士彪. ZL201510873440.2,2015.11.23,全连接引导的数字图像滤波方法和系统,中国,已授权
5.张晓鹏, 张飞虎, 代龙泉, 向世明,徐士彪. ZL201510872635.5,2015.11.23,基于分割图的数字图像滤波方法和系统,中国,已授权.
6.郗润平, 马成丞, 张吉光, 徐士彪, 孟维亮, 张晓鹏. ZL201711438764.9,2019.03.19,一种基于显著图像块分析的图像运动模糊去除方法,已授权
7.徐士彪, 孟维亮, 郭建伟, 张晓鹏. ZL201810788765.4,2020.10.12,基于多尺度三维先验信息的屋顶分割方法、系统与设备,已授权
8.徐士彪, 孟维亮, 郭建伟, 张晓鹏. ZL201810794383.2,2020.07.08,基于多分辨率三维统计信息的屋顶分割方法、系统及设备,已授权
9.郭建伟,徐士彪,严冬明,孟维亮,张晓鹏. CN201811052482.X,2018.09.10,基于多视角图像的过程式植物模型重建方法,已公开
10.徐士彪、张宇阳、孟维亮、张吉光、张晓鹏. CN202010437242.2,2020.05.22,多视角图像一致性的无监督深度预测方法、系统、装置,已公开
11.张吉光、徐士彪、潘冰冰、孟维亮、张晓鹏. CN202010440471.X,2020.05.22,基于主动筛选的半监督病灶检测系统,已公开


学术奖励

1.三维复杂场景认知的关键技术研究,陕西省高等学校科学技术奖,陕西省教育厅,一等奖,2017(王映辉,张晓鹏,宁小娟,徐士彪(4/11),郝雯,代龙泉,李尔,郭建伟,吕志勇,李晔,石争浩)。


指导学生

   
协助指导学生发表论文情况(本人均为通信或第二作者)

1.张吉光发表SCI论文2篇,国际会议论文2篇,博士学位论文副导师,University of Mysore,博士,2015.06-2018.10(已毕业)
2.杨东明发表SCI论文1篇,国内核心期刊2篇,硕士学位论文副导师,中科院文献情报中心,硕士,2015.06-2017.12(已毕业)
3.杨真核心期刊2篇,硕士学位论文副导师,中科院文献情报中心,硕士,2015.06-2017.12(已毕业)
4.秦悦发表SCI论文2篇,EI论文1篇,北京工业大学,硕士,2016.06-2018.06(已毕业)
5.达铖发表CVPR论文1篇,中科院自动化所,博士,2017.01-2018.06(已毕业)
6.程光亮发表SCI论文TGRS1篇,中科院自动化所,博士,2017.01-2017.12(已毕业)
7.郑马娜发表SCI论文1篇,北京工业大学,硕士,2019.06-2020.06(已毕业)
8.马成丞发表SCI论文1篇,申请专利1项,中科院自动化所,硕士,2016.09-至今
9.张宇阳发表SCI论文TIP1篇,中科院自动化所,硕博,2015.09-至今
10.赵勇发表ICCV论文1篇,发表IROS论文1篇,发表SCI论文TGRS1篇,西北工业大学,硕博,2017.09-至今
11.马文广发表SCI论文2篇,北京工业大学,硕士,2019.06-至今

指导或协助指导学生(中国科学院大学&中科院自动化所在读)