个人简介

王小刚，副教授，硕导，目前任职于西南大学计算机与信息科学学院。于北京航空航天大学获博士学位，博士就读期间，于加拿大西蒙弗雷泽大学（Simon Fraser University）交流访问一。于中国农业大学获得本科与硕士学位。目前主要研究兴趣包括高质量三维重建、2D/3D计算机视觉、机器学习、虚拟现实、数字孪生等领域。目前共发表论文20余篇，其中包括 ACM Transaction on Graphics（ACM TOG）, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Conference on Computer Vision and Pattern Recognition（CVPR）, IEEE International Conference on Computer Vision（ICCV）, Neural Information Processing Systems(NeurIPS),ACM International Conference on Multimedia (MM)等顶级期刊/会议论文。获得国家发明专利和国际发明专利授权共9项（美国发明专利4项、中国发明专利5）。获得2015年度 IEEE International Conference on Multimedia Big Data国际会议最佳论文奖。

教学情况

主要讲授计算机科学与技术专业 《虚拟现实》《虚拟现实技术基础》《大数据可视化技术》等课程。

代表性论文：

[1] XiShu Fan, Zexian Liu, Junlin Chang, Hongyu Wu, Xiaogang Wang, Aimin Hao. 3D Dental Model Segmentation with Geometrical Boundary Preserving. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),2025.（CCF-A类国际会议，已接收）

[2] Yuhang Cheng, Zhiyuan Wang, JiaLan He, and Xiaogang Wang. Winding Number-guided Edge-Preserving Implicit Neural Representation of CAD Surfaces. IEEE International Conference on Robotics and Automation (ICRA),2025.（CCF-B类国际会议, 已接收）

[3] Yuhang Cheng, Yu Zhang, Xiaogang Wang. Learing 3D Volume Cloud from Single Image. ACM International Conference on Multimedia Retrieval (ICMR),2025. （CCF-B类国际会议, 已接收）

[4] Xiaogang Wang, Yuhang Cheng, Ziyang Fan, and Kai Xu. Learning to transfer heterogeneous translucent materials from a 2D image to 3D models. In Proceedings of the 32nd ACM International Conference on Multimedia (MM), pages 3440-3448, 2024.（CCF-A类国际会议）

[5] Yinglong Li, Hongyu Wu, Xiaogang Wang, Qingzhao Qin, Yijiao Zhao, Yong Wang, and Aimin Hao. Facecom: Towards high-fidelity 3d facial shape completion via optimization and inpainting guidance. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 2177-2186, 2024.（CCF-A类国际会议）

[6] Xiaogang Wang, Liang Wang, Hongyu Wu, Guoqiang Xiao, and Kai Xu. Parametric primitive analysis of cad sketches with vision transformer. IEEE Transactions on Industrial Informatics (TII), 2024.（中科院SCI一区， IF:11.7）

[7] Yuhang Cheng, Ziyang Fan, Hongyu Wu, and Xiaogang Wang. High-order differential regularizing implicit surface representation of point cloud. In 2024 IEEE International Conference on Multimedia and Expo (ICME),2024.（CCF-B类国际会议,Oral）

[8] Dan Mei and Xiaogang Wang. Finernet: A coarse-to-fine approach to learning high-quality implicit surface reconstruction. Computer Graphics International Conference (CGI), pages 147-158. Springer, 2023.（CCF-C类国际会议,Oral）

[9] Liang Wang and Xiaogang Wang. PPI-NET: end-to-end parametric primitive inference. Computer Graphics International Conference (CGI), pages 67-78. Springer, 2023.（CCF-C类国际会议，Oral）

[10] Xiaogang Wang, Xun Sun, Sinyu Cao, Kai Xu, Bin Zhou. Learning Fine-Grained Segmentation of 3D Shapes without Part Labels. IEEE Conference on Computer Vision and Patern Recognition (CVPR), 2021.（CCF-A类国际会议）

[11] Xiaogang Wang, Yuelang Xu, Kai Xu, Andrea Tagliasacchi, Bin Zhou, Ali Mahdavi Amiri, Hao Zhang.PIE-Net: Learning Parametric Inference of Edges for Point Clouds. 34th Conference on Neural Information Processing Systems (NeurIPS), 2020. (CCF-A类国际会议)

[12] Dongqing Zou, Xiaowu Chen, Guangying Cao，Xiaogang Wang. Unsupervised Video Matting via Sparse and Low-Rank Representation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020.（中科院SCI一区，CCF-A类国际期刊,IF:20.8）

[13] Xiaogang Wang, Bin Zhou, Yahao Shi, Xiaowu Chen, Qingping Zhao and Kai Xu. Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes. IEEE Conference on Computer Vision and Patern Recognition (CVPR), 2019. (Oral presentation) （CCF-A类国际会议, Oral）

[14] Haiyue Fang*, Xiaogang Wang*(共同第一作者), Zheyuan Cai, Xun Sun and Bin Zhou. Learning semantic abstraction of shape via 3D region of interest. Graphical Models (GM), 2019.（CCF-B类国际期刊）

[15] Xiaogang Wang, Bin Zhou, Haiyue Fang, Xiaowu Chen, Qingping Zhao and Kai Xu. Learning to Group and Label Fine-Grained Shape Components. ACM Transactions on Graphics (SIGGRAPH Asia), 2018. （中科院SCI一区，CCF-A类国际期刊）

[16] Xiaogang Wang, Bin Zhou, Zongji Wang, Dongqing Zou, Xiaowu Chen and Qingping Zhao. Efficiently consistent affinity propagation for 3D shapes co-segmentation. Visual Computer (TVC), 2018. （CCF-C类国际期刊）

[17] Yafei Song, Jia Li, Xiaogang Wang, Xiaowu Chen. Single Image Dehazing Using Ranking Convolutional Neural Network[J]. IEEE Transactions on Multimedia (TMM), 2017. （中科院SCI一区，CCF-B类国际期刊）

[18] Yafei Song, Xiaowu Chen, Xiaogang Wang, Yu Zhang, Jia Li. 6-DOF Image Localization From Massive Geo-Tagged Reference Images[J]. IEEE Transactions on Multimedia (TMM), 2016. （中科院SCI一区，CCF-B类国际期刊）

[19] Yafei Song, Xiaowu Chen, Xiaogang Wang, Yu Zhang, Jia Li. Fast Estimation of Relative Poses for 6-DOF Image Localization. IEEE International Conference on Multimedia Big Data (BigMM), 2015. (最佳会议论文奖)

[20] Dongqing Zou, Xiaowu Chen, Guangying Cao, Xiaogang Wang. Video Matting via Sparse and Low-Rank Representation. IEEE International Conference on Computer Vision (ICCV), 2015. （CCF-A类国际会议）

[21] Han Zhang, Xiaowu Chen, Yu Zhang, Jia Li, Qing Li, Xiaogang Wang. Cuboids detection in RGB-D images via Maximum Weighted Clique. IEEE International Conference on Multimedia and Expo (ICME), 2015. （CCF-B类国际会议）

[22] Xiaogang Wang, Li Li and Wenting Chai. Geometric modeling of broad-leaf plants leaf based on B-spline[J]. Mathematical and Computer Modelling (MCM), 2013. （SCI一区期刊）

发明专利(已授权)：

[1] 中国发明专利授权，名称：一种CAD模型运动部件及运动属性联合解析方法及装置。已授权（ZL 2023 1 0332610.0），2024.04.19

[1] 美国发明专利授权，名称：METHOD AND APPARATUS FOR PARSING AND PROCESSING THREE-DIMENSIONAL CAD MODEL.已授权（US 10,489,914 B2），2019.11.26

[2] 美国发明专利授权，名称： CO-SEGMENTATION METHOD AND APPARATUS FOR THREE-DIMENSIONAL MODEL SET.已授权（US 10,672,130 B2），2020.06.02

[3] 美国发明专利授权，名称： METHOD FOR VIDEO MATTING VIA SPARSE AND LOW-RANK REPRESENTATION.已授权（US 10,235,571 B2），2019.3.19

[4] 美国发明专利授权，名称： IMAGE DEHAZING METHOD。已授权（US 10,504,209 B2），2019.12.10

[5] 中国发明专利授权，名称：一种稀疏和低秩联合表达的视频前景对象精准提取。已授权（ZL 2015 1 0695505.9），2018.04.06

[6] 中国发明专利授权，名称：三维模型集共分割方法及装置。已授权（ZL 2017 1 0088613.9），2020.04.21

[7] 中国发明专利授权，名称：排序卷积神经网络构建方法及其图像处理方法与装置。申请时间：2016.07.12。已授权（ZL 2016 1 0545516.9），2019.09.10

[8] 中国发明专利授权，名称：三维模型的解析处理方法和装置。已授权（ZL 2017 1 0850541.9），2021.01.19

备注

热忱欢迎有志于做顶级学术成果的学生，欢迎感兴趣的学生（本科、研究生）随时发邮件或来办公室（西南大学25教1806室）咨询交流!!!