About Me

I am currently a Ph.D. student at the SICE from the University of Electronic Science and Technology of China (UESTC), supervised by Prof. Shuaicheng Liu and Prof. Bing Zeng. I received my Master’s degree at École Nationale Supérieure des Télécommunications de Bretagne, supervised by Prof. Laurent Brisson. Before that, I got my Bachelor’s degree from the University of Electronic Science and Technology of China (UESTC). My research interests include image alignment, and generative model.

News

  • 2024.07:   One paper is accepted to ECCV 2024.
  • 2024.06:   One paper is accepted to TCSVT.
  • 2024.03:   One paper is accepted to TIP.
  • 2024.02:   One paper is accepted to ToG.
  • 2024.02:   Two papers are accepted to CVPR 2024.

Publications

2024

sym

PointGPT: Boosting 3D Point Cloud Registration using Generative Point-Cloud Pairs for Training

IEEE/CVF European Conference on Computer Vision (ECCV), 2024

Suyi Chen, Hao Xu, Haipeng Li, Kunming Luo, Guanghui Liu, Chi-Wing Fu, Ping Tan, Shuaicheng Liu

Paper | Video | Code | BibTex

sym

CodingHomo: Bootstrapping Deep Homography with Video Coding

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)

Yike Liu, Haipeng Li, Shuaicheng Liu, Bing Zeng

Paper | Code | BibTex

sym

Single-Image-Based Deep Learning for Segmentation of Early Esophageal Cancer Lesions

IEEE Transactions on Image Processing (TIP)

Haipeng Li*(equal contribution), Dingrui Liu*, Yu Zeng, Shuaicheng Liu, Tao Gan, Nini Rao, Jinlin Yang, Bing Zeng

Paper | Code | BibTex

sym

DMHomo: Learning Homography with Diffusion Models

ACM Transactions on Graphics (ToG), Present at SIGGRAPH 2024

Haipeng Li, Hai Jiang, Ao Luo, Ping Tan, Haoqiang Fan, Bing Zeng, Shuaicheng Liu

[Paper] | Video | [Code: Pytorch] | BibTex

sym

RecDiffusion: Rectangling for Image Stitching with Diffusion Models

IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024

Tianhao Zhou*, Haipeng Li*(equal contribution), Ziyi Wang, Ao Luo, Chen-Lin Zhang, Jiajun Li, Bing Zeng, Shuaicheng Liu

Paper | Video | Code | BibTex

sym

HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions

IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024

Hao Xu, Haipeng Li, Yinqiao Wang, Shuaicheng Liu, Chi-Wing Fu

Paper | Video | Code | BibTex

sym

GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learning

International Journal of Computer Vision (IJCV)

Haipeng Li, Kunming Luo, Bing Zeng, Shuaicheng Liu

[Paper] | [Code: Pytorch] | BibTex

2023

sym

Supervised Homography Learning with Realistic Dataset Generation

International Conference on Computer Vision (ICCV), 2023

Hai Jiang*, Haipeng Li*(equal contribution), Songchen Han, Haoqiang Fan, Bing Zeng, Shuaicheng Liu

[Paper] | [Code: Pytorch] | BibTex

sym

Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint

Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2023.

Hai Jiang*, Haipeng Li*(equal contribution), Yuhang Lu, Songchen Han, Shuaicheng Liu

[Paper] | [Code: Pytorch] | BibTex

2021

sym

GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning

International Conference on Computer Vision (ICCV), 2021.

Haipeng Li, Kunming Luo, Shuaicheng Liu

[Paper] | [Code: Pytorch] | BibTex

sym

DeepOIS: Gyroscope-Guided Deep Optical Image Stabilizer Compensation

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)

Shuaicheng Liu, Haipeng Li, Zhengning Wang, Jue Wang, Shuyuan Zhu, Bing Zeng

[Paper] | [Code: Pytorch] | BibTex

Education

  • 2022.09 - Present, Ph.D. candidate, University of Electronic Science and Technology of China (UESTC)
  • 2017.07 - 2020.03, M.Sc., École Nationale Supérieure des Télécommunications de Bretagne
  • 2013.09 - 2017.06, B.E., University of Electronic Science and Technology of China (UESTC)

Experience

  • 2020.06 - 2022.09, Researcher, Megvii Research

Academic Services

  • Journals: TPAMI, TIP, TCSVT
  • Conferences: CVPR2024, MM2024, AAAI2025, ICLR2025