I am currently a postdoctoral researcher working with Prof. Boxin Shi and Chao Xu at Camera Intelligence Lab, Peking University (PKU). Before that, I received my Ph.D. in 2023, advised by Prof. Yuchao Dai, at the School of Electronics and Information, Northwestern Polytechnical University (NPU), Xi'an, China.
My research mainly focuses on camera pose estimation, image rectification, temporal super-resolution, and 3D reconstruction, especially regarding the rolling shutter camera. I am also interested in low-level geometric problems (e.g. structure from motion, SLAM) and image restoration tasks (e.g. deblurring).
binfan [at] mail.nwpu.edu.cn
No. 1 Dongxiang Road, Chang'an District, Xi'an, China, 710129
(+86)-187-1738-1424
Ph.D. in Information and Communication Engineering
Apr 2019 - Apr 2023
NPU, Shaanxi, China
Advisor: Prof. Yuchao Dai
M.E. in Control Science and Engineering
Sep 2016 - Mar 2019
NPU, Shaanxi, China
Advisor: Prof. Chunhui Zhao
B.S. in Statistics
Sep 2012 - Jun 2016
NPU, Shaanxi, China
Unified Video Reconstruction for Rolling Shutter and Global Shutter Cameras
IEEE Transactions on Image Processing (TIP), 2024
[ Paper | Code | Supplementary Video ]
Self-Supervised Learning for Rolling Shutter Temporal Super-Resolution
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024
[ Paper | Code | Supplementary Video ]
Learning Bilateral Cost Volume for Rolling Shutter Temporal Super-Resolution
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024
[ Project Page | Paper | Code | Supplementary Video ]
Rolling Shutter Inversion: Bring Rolling Shutter Images to High Framerate Global Shutter Video
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
[ Paper | Code | Supplementary Video ]
Joint Appearance and Motion Learning for Efficient Rolling Shutter Correction
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[ Project Page | Paper | Poster | Video | Code ]
Context-Aware Video Reconstruction for Rolling Shutter Cameras
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
[ Project Page | Paper | Poster | Code ]
Inverting a Rolling Shutter Camera: Bring Rolling Shutter Images to High Framerate Global Shutter Video
IEEE International Conference on Computer Vision (ICCV), 2021
[ Project Page | Paper | Poster | Code ]
SUNet: Symmetric Undistortion Network for Rolling Shutter Correction
IEEE International Conference on Computer Vision (ICCV), 2021
[ Project Page | Paper | Poster | Code ]
Rolling-Shutter-Stereo-Aware Motion Estimation and Image Correction
Computer Vision and Image Understanding (CVIU), 2021
[ Project Page | Paper ]
Differential SfM and Image Correction for a Rolling Shutter Stereo Rig
Image and Vision Computing (IVC), 2022
[ Project Page | Paper ]
Rolling Shutter Camera: Modeling, Optimization and Learning
Machine Intelligence Research (MIR), 2023
[ Project Page | Paper ]
RS-DPSNet: Deep Plane Sweep Network for Rolling Shutter Stereo Images
IEEE Signal Processing Letters (SPL), 2021
[ Paper ]
Fast and Robust Differential Relative Pose Estimation with Radial Distortion
IEEE Signal Processing Letters (SPL), 2021
[ Paper ]
Learning a Task-Specific Descriptor for Robust Matching of 3D Point Clouds
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022
[ Project Page | Paper ]
VRNet: Learning the Rectified Virtual Corresponding Points for 3D Point Cloud Registration
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022
[ Project Page | Paper ]
Searching Dense Point Correspondences via Permutation Matrix Learning
IEEE Signal Processing Letters (SPL), 2022
[ Paper ]
Homography-Based Camera Pose Estimation with Known Gravity Direction for UAV Navigation
Science China Information Sciences (Sci. China Inf. Sci.), 2021
[ Paper ]
Relative Pose Estimation for Stereo Rolling Shutter Cameras
IEEE International Conference on Image Processing (ICIP), 2020
[ Paper ]
Pose Estimation for Multi-Camera Systems
IEEE International Conference on Unmanned Systems (ICUS), 2017
[ Paper ]