Hainan Cui

崔海楠

副研究员, 硕导

中国科学院自动化研究所

崔海楠,中国科学院自动化研究所副研究员,硕士生导师。2016年博士毕业于中国科学院自动化研究所,2011年本科毕业于华南理工大学计算机科学与工程学院。主要从事三维计算机视觉理论和应用的研究,尤其专注于基于图像的大规模场景三维建模研究,已在IEEE TIP、ISPRS P&RS、PR、CVPR、AAAI、IROS等国际期刊和会议发表论文30余篇。主要工作已被三维建模主流代码库OpenMVG和Theia实现和开源。获得国家自然科学基金青年基金、国家自然科学基金面上基金、国家自然科学基金联合重点基金等多个国家项目资助,同时得到国内企业(华为、商汤和滴滴等)的长期资助,获得2020年CCF-滴滴盖亚青年学者科研基金杰出项目称号。

个人主页:https://people.ucas.edu.cn/~cuihainan

Publications

PanoPose: Self-supervised Relative Pose Estimation for Panoramic Images. IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2024.

DOI

Revisiting Global Translation Estimation with Feature Tracks. IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2024.

DOI

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

DOI

PanoVLM: Low-Cost and Accurate Panoramic Vision and LiDAR Fused Mapping. ISPRS Journal of Photogrammetry and Remote Sensing, 206: 149-167, 2023.

Code 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

Multi-Camera-LiDAR Auto-Calibration by Joint Structure-from-Motion. IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022.

DOI

Active Learning Based 3D Semantic Labeling From Images and Videos. IEEE Transactions on Circuits and Systems for Video Technology, 32(12): 8101-8115, 2022.

DOI

MMA: Multi-Camera Based Global Motion Averaging. AAAI Conference on Artificial Intelligence, AAAI 2022.

DOI

Reconstruction of lines and planes of urban buildings with angle regularization. ISPRS Journal of Photogrammetry and Remote Sensing, 165: 54-66, 2020.

DOI

3D Scene Gemoetry and Semantic Reconstruction. in Advances in Visual Information Processing, Shanghai Jiaotong University Press, 2019. (in Chinese).

Voting-based Incremental Structure-from-Motion. International Conference on Pattern Recognition, ICPR 2018.

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

Robust global translation averaging with feature tracks. International Conference on Pattern Recognition, ICPR 2016.

DOI