Pei An websites

I was a Postdoctoral Researcher in Huazhong University of Science and Technology (from 2024-2026) and will become an Associate Researcher in Huazhong Agricultural University. I love hiking and thinking. Up to now, I have published 40+ journal and conference papers, including CVPR, ICCV, ECCV, IJCV, IEEE Trans. and so on.

Research Interests

Focusing on two foundamental problems about image-to-point-cloud (I2P) perception:
(1) Image-to-point-cloud registration.
(2) Applications of image-to-point-cloud registration, such as visual SLAM and Gaussian splatting.

News

[2026.06] Two paper about I2P registration was accepted by ECCV 2026 (as first author). [2026.02] One paper about I2P registration was accepted by CVPR 2026 (as first author).
[2025.08] One paper about I2P registration was accepted by IJCV 2025 (as first author).
[2025.06] One paper about I2P registration was accepted by ICCV 2025 (as first author).
[2025.04] One paper about I2P registration was accepted by IJCAI 2025 (as first author).

Projects

(1) National Natural Science Foundation of China (PI), about I2P registration, 2025
(2) China Postdoctoral Science Foundation (PI), about I2P registration, 2025
(3) China Postdoctoral Science Foundation (PI), about I2P registration, 2024
(4) HUST Postdoctoral Science Special Funding (PI), about I2P registration, 2024
(5) National Key R&D Program of China (sub-project, PI), about multi-modal perception, 2024

Recent publications

[2026-1] Pei An, Junfeng Ding, Jiaqi Yang, Yulong Wang, Liangliang Nan, and et al. Hg-I2P: Bridging modalities for generalizable image-to-point-cloud registration via heterogeneous graphs, in Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR), 2026, Accepted.
[2026-2] Pei An, Jiaqi Yang, Yulong Wang, Siwen Quan, and Liangliang Nan. OCA: ODE-Driven Cross-Attention for Image-to-Point-Cloud Registration, in Proceedings of European Conference on Computer Vision (ECCV), 2026, Accepted.
[2026-3] Pei An, Muyao Peng, Junfeng Ding, Jiaqi Yang, and Liangliang Nan. Ex-Sim(3)-Reg: 2D-3D Correspondence Pruning via Extended Sim(3) Registration, in Proceedings of European Conference on Computer Vision (ECCV), 2026, Accepted.
[2025-1] Pei An, Jiaqi Yang, You Yang, and et al. MinCD-PnP: Learning 2D-3D Correspondences with Approximate Blind PnP, in Proceedings of International Conference on Computer Vision (ICCV), 2025, 26519-26528.
[2025-2] Pei An, Jiaqi Yang, Jie Ma, You Yang, and et al. Top-I2P: Explore Open-Domain Image-to-Point Cloud Registration using Topology Relationships, in Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), 2025, 674-683.
[2025-3] Pei An, You Yang, Jiaqi Yang, and et al. Enhance Image-to-Point-Cloud Registration with Beltrami Flow. International Journal of Computer Vision (IJCV), 2025, 133(12): 8589-8616.

Concat

email: anpei96@hust.edu.cn