管涛

·Personal Information

Current position: 英文主页 >Personal Information

       博士,教授,博士生导师。2008年毕业于华中科技大学,获得通信与信息系统专业博士学位,2010年进入华中科技大学计算机学院数字媒体实验室从事教学科研工作。

      长期从事计算机视觉与计算机仿真方面的研究工作,主要研究方向包括: 数字孪生与建模仿真、三维渲染引擎、基于图像的三维建模增强与虚拟现实

IEEE/ ACM Trans、ICCV、CVPR、ECCV等期刊会议上发表高水平论文20余篇:

会议论文:

ReinforceNS: Reinforcement Learning-based Multi-start Neighborhood Search for Solving the Traveling Thief Problem. IJCAI 2024(CCF A

C2F2NeUS: Cascade Cost Frustum Fusion for High Fidelity and Generalizable Neural Surface Reconstruction. ICCV 2023(CCF A

Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR 2023(CCF A

Self-Supervised Multi-view Stereo via Adjacent Geometry Guided Volume Completion. ACMMM 2022(CCF A

Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation. NeurIPS 2020(CCF A

Mesh-Guided Multi-View Stereo with Pyramid ArchitectureCVPR 2020(CCF A

Attention-Aware Multi-View Stereo. CVPR 2020(CCF A

P-MVSNet: Learning Patch-wise Matching Confidence Aggregation for Multi-View Stereo. ICCV 2019(CCF A

Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation. ICCV 2019(CCF A

Taking A Closer Look at Domain Shift:Category-level Adversaries for Semantics Consistent Domain Adaptation. CVPR 2019(CCF Aoral

      Macro-Micro Adversarial Network for Human Parsing. ECCV 2018(CCF B)

       Interactive on-device Mobile Landmark Recognition With Compact Binary Codes. ICASSP 2015(CCF B)

       期刊论文:

       Transformer-based 3D Face Reconstruction with End-to-end Shape-preserved Domain Transfer. IEEE Transactions on Circuits and Systems for Video Technology 2022

       Category-Level Adversarial Adaptation for Semantic Segmentation using Purified Features. IEEE Transactions on Pattern Analysis and Machine Intelligence 2021

       DeepFusion: A simple way to improve traditional multi-view stereo methods using deep learning. Knowledge-Based Systems 2021

       A visibility-based surface reconstruction method on the GPU. Computer Aided Geometric Design 2021

       On-Device Mobile Landmark Recognition Using Binarized Descriptor with Multi-Feature Fusion. ACM Transactions on Intelligent Systems and Technology 2015

       Projected Residual Vector Quantization for ANN Search. IEEE Multimedia Magazine 2014

       Efficient Bag-of-Features Generation and Compression for On-DeviceMobile Visual Location Recognition. IEEE Multimedia Magazine 2014

       On-Device Mobile Visual Location Recognition by Integrating Visionand Inertial Sensors. IEEE Transactions on Multimedia 2013

       Real Time Camera Pose Estimation for Wide Area Augmented RealityApplications. IEEE Computer Graphics and Applications 2011

       Registration Based on Scene Recognition and Natural FeaturesTracking Techniques for Wide-area Augmented Reality Systems. IEEE Transactions on Multimedia 2009

作为项目负责人主持的科研项目如下:

2018.1-2020.12,增强现实核心算法软件设计技术研究,预研计划

2017.1-2018.12,面向增强现实的三维建模和自动配准技术,横向

2017.5-2018.12,多元数据融合三维建模技术,横向

2016.1-2017.12,无人机自主**与**技术,横向

2016.1-2016.5,三维点云处理与建模技术,横向

2016.1-2016.10,×××GIS系统设计,横向

2015.5-2015.6,三维重构软件设计,横向

2015-2016,基于无人机影像的地震灾情时空一体化建模解析技术,国家公益性行业科研专项

2015-2016,仿真三维建模技术,横向

2013.6-2015.6,基于增强现实的××××仿真关键技术研究,预研基金

2013.6-2014.6,移动视觉定位关键技术研究,自主创新基金

2013.1-2016.12,移动增强现实大范围定位与追踪关键技术研究,国家自然科学基金

2012.6-2014.6,基于×××技术的××××环境构建关键技术研究,预研基金

2011-2015,虚拟××环境××仿真平台,“十二五”预研计划

2010-2012 ,未知场景下的增强现实虚实注册关键技术研究,国家自然科学基金青年基金

2008-2010,增强现实几何一致性恢复方法研究,中国博士后科学基金面上项目

欢迎优秀本科以及硕士毕业生保送或报考本课题组,有意者可将简历发送至本人邮箱。

联系方式:qd_gt@hust.edu.cn (邮箱)

基本要求:计算机相关专业毕业,熟悉C、C++,具备较好的编程能力以及独立思考和解决问题的能力