基本信息

肖俊  教授  博士生导师

         北京市科技新星

         中国科学院青促会优秀会员

电子邮件: xiaojun@ucas.ac.cn
通信地址: 北京市玉泉路甲19号
邮政编码: 100049

研究领域

计算机视觉,AI+

招生信息

招收人工智能(智能科学与技术)、计算机科学与技术、软件工程等相关专业的考生

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
图形图像处理
AI+交叉学科

工作经历

   
工作简历
2016-11~现在, 中国科学院大学, 教授
2010-05~2016-11,中国科学院大学, 副教授
2010-03~2010-05,中国科学院研究生院, 讲师
2008-04~2010-03,中国科学院研究生院, 师资博士后

出版信息

代表性论文:

(1)     Efficient Single Correspondence Voting for Point Cloud Registration [J]. IEEE Transactions on image processing, 2024

(2)     SPDET: Edge-Aware Self-Supervised Panoramic Depth Estimation Transformer With Spherical Geometry [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023

(3)     PartCom: Part Composition Learning for 3D Open-Set Recognition [J]. International Journal of Computer Vision, 2023

(4)     NR-MVSNet: Learning Multi-view Stereo based on Normal Consistency and Depth Refinement [J]. IEEE Transactions on Image Processing, 2023

(5)     Decompose Novel into Known: Part Concept Learning For 3D Novel Class Discovery [C]. NeurIPS, 2023

(6)     VectorFloorSeg: Two-Stream Graph Attention Network for Vectorized Roughcast Floorplan Segmentation[C], CVPR 2023 (HIGHLIGHT paper)

(7)     SSF: Accelerating Training of Spiking Neural Networks with Stabilized Spiking Flow [C]. ICCV 2023

(8)     Combating Spurious Correlations in Loose-fitting Garment Animation Through Joint-Specific Feature Learning [C]. Pacific Graphics 2023

(9)     Progressive Graph Matching Network for Correspondences[C]. Pacific Graphics, 2023

(10)  Poisson-Based Image Editing for Semi-Supervised Vitiligo Lesion Segmentation with Limited Annotations [J]. Computers in Biology and Medicine, 2023

(11)  Landmark Guided 4D Facial Expression Generation[C]. SIGGRAPH Asia Poster, 2023

(12)  DS-MVSNet: Unsupervised Multi-view Stereo via Depth Synthesis[C], ACM Multimedia, 2022

(13)  ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation[C], AAAI, 2022

(14)  Context-Aware 3D Point Cloud Semantic Segmentation With Plane Guidance[J], IEEE Transactions on Multimedia, 2022

(15)  MEMformer: Transformer-based 3D Human Motion Estimation from MoCap Markers[C], SIGGRAPH Asia, 2022

(16)  Registration Method for Point Clouds of Complex Rock-mass Based on Dual Structure Information[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022

(17)  Dynamic video mix-up for cross-domain action recognition [J]. Neurocomputing, 2022

(18)  Joint Specular Highlight Detection and Removal in Single Images via Unet-Transformer[J], Computational Visual Media, 2022

(19)  Accurate Lung Nodules Segmentation with Detailed Representation Transfer and Soft Mask Supervision[C].ICME, 2022

(20)  Single-Image Specular Highlight Removal via Real-World Dataset Construction[J]. IEEE Transactions on Multimedia, 2021

(21)  A Novel Rock-Mass Point Cloud Registration Method Based on Feature Line Extraction and Feature Point Matching [J]. IEEE Transactions on Geoscience and Remote Sensing, 2021

(22)  Efficient Pairwise 3D Registration of Urban Scenes Via Hybrid Structural Descriptors [J]. IEEE Transactions on Geoscience and Remote Sensing, 2021

(23)  Data-driven Floor Plan Understanding in Rural Residential Buildings via Deep Recognition [J], Information Sciences, 2021

(24)  Unsupervised Learning of Disentangled 3D Representation from a Single Image [C], Eurographics, 2021

(25)  End-to-end 3D Point Cloud Instance Segmentation without Detection[C]. CVPR 2020

(26)  Blending Surface Segmentation and Editing for 3D Models [J], IEEE Transactions on Visualization and Computer Graphics, 2020

(27)  Deep Specular Highlight Removal for Single Real-world Image [C], SIGGRAPH Asia Poster, 2020

(28)  Extracting Cycle-Aware Feature Curve Networks from 3D Models [J], Computer-Aided Design, 2020

(29)  Accurate Rock-mass Extraction from Terrestrial Laser Point Clouds via Multi-scale and Multi-view Convolutional Feature Representation [J]. IEEE Transactions on Geoscience and Remote Sensing, 2020

(30)  Efficient Rock-Mass Point Cloud Registration Using n-Point Complete Graphs [J]. IEEE Transactions on Geoscience and Remote Sensing, 2020

(31)  CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation [C]AAAI, 2020

(32)  A Wavelet Energy Decomposition Signature for Robust Non-Rigid Shape Matching [C]SIGGRAPH Asia, 2019

(33)  An automatic 3D registration method for rock mass point clouds based on plane detection and polygon matching [J], The Visual Computer, 2019

(34)  A fast registration algorithm of rock point cloud based on spherical projection and feature extraction [J], Frontiers of Computer Science, 2019

(35)  Feature Curve Network Extraction via Quadric Surface Fitting [C]Pacific Graphics 2019

(36)  Fast and Error-Bounded Space-Variant Bilateral Filtering [J]Journal of Computer Science and Technology, 2019

(37)  Help Label Me: A Fast Auxiliary Method for Labeling Image and Using It in ChangE’s CCD Data [C], ICIG2019, 2019

(38)  A survey on algorithms of hole filling in 3D surface reconstruction [J], The Visual Computer, 2018

(39)  Filtering method of rock points based on BP neural network and principal component analysis [J], Frontiers of Computer Science, 2018

科研活动

主要科研项目

(1)元宇宙中三维场景感知与理解关键技术

(2)道路交通场景的环境目标三维状态感知与验证

(3)基于多模态数据的银屑病和特应性皮炎智能辨别方法研究

(4)基于序列化高清图像的大规模场景实时三维重建与智能解析方法

(5)深度学习驱动的弱监督三维场景理解及实例重建

(6)面向BIM的参数化模型重建与分析

(7)三维数字化机房重建算法研究

(8)山地致灾风险评估平台的软件研发

(9)面向月球场景的高精度三维重建与语义分割技术研究

(10 三维非连续性工程计算软件研发及示范应用

(11 面向大规模岩体点云的自适应滤波方法研究

(12 任意临空面条件下的关键块体识别理论研究

(13 面向工程计算的岩体三维重建理论与方法研究

(14 面向岩体结构面提取的大规模点云分析方法研究

(15 面向工程计算的三维重建技术研究