高翔,中国科学院自动化研究所副研究员。2019年于中国科学院自动化研究所获得博士学位,2012年、2015年于中国海洋大学工程学院分别获得学士、硕士学位。研究方向为三维计算机视觉,基于图像的大规模场景三维重建。在相关领域国际期刊(IJCV、IEEE T-IP/T-NNLS/T-CYB/T-CSVT、ISPRS P&RS、PR等)和国际会议(CVPR、ECCV等)上发表论文30余篇,主持科研项目6项,其中包括国家、省部级科研项目5项。担任中国图像图形学学会三维视觉专委会委员以及多个国际国内期刊会议审稿人,如IEEE TIP、TCYB、TGRS、TCSVT等。研究成果获CVPR 2019大时间跨度视觉定位竞赛冠军、VALSE 2021焦点论文等。所开发的基于图像的大规模场景三维重建系统已在城市高精地图构建、古建三维数字化保护、三维数字城市等多个领域得到了实际应用。

个人主页:https://xgao-3dv.github.io

Publications

Large-Scale Structure from Motion: A Survey. Journal of Computer-Aided Design and Computer Graphics, 2024. (in Chinese).

DOI

IRAv3+: Hierarchical Incremental Rotation Averaging via Multiple Connected Dominating Sets. IEEE Transactions on Circuits and Systems for Video Technology, 34(4): 3049-3055, 2024.

DOI

Recent Advances in Conventional and Deep Learning-Based Depth Completion: A Survey. IEEE Transactions on Neural Networks and Learning Systems, 35(3): 3395-3415, 2024.

DOI

McSfM: Multi-camera Based Incremental Structure-from-Motion. IEEE Transactions on Image Processing, 32: 6441-6456, 2023.

DOI

IRAv3: Hierarchical Incremental Rotation Averaging on the Fly. IEEE Transactions on Circuits and Systems for Video Technology, 33(4): 2001-2006, 2023.

DOI

IRA++: Distributed Incremental Rotation Averaging. IEEE Transactions on Circuits and Systems for Video Technology, 32(7): 4885-4892, 2022.

DOI

Incremental Translation Averaging. IEEE Transactions on Circuits and Systems for Video Technology, 32(11): 7783-7795, 2022.

DOI

Incremental Rotation Averaging. International Journal of Computer Vision, 129: 1202–1216, 2021.

DOI

Complete Scene Reconstruction by Merging Images and Laser Scans. IEEE Transactions on Circuits and Systems for Video Technology, 30(10): 3688-3701, 2020.

DOI

Urban Scene Vectorized Modeling Based on Contour Deformation. ISPRS International Journal of Geo-Information, 9(3), 162, 2020.

DOI

Visual Localization Using Sparse Semantic 3D Map. IEEE International Conference on Image Processing, ICIP 2019.

DOI

Batched Incremental Structure-from-Motion. International Conference on 3D Vision, 3DV 2017.

DOI

CSFM: Community-based structure from motion. IEEE International Conference on Image Processing, ICIP 2017.

DOI

HSfM: Hybrid Structure-from-Motion. IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017.

DOI