Biography
I am Shengjie Zhu, an Applied Scientist at Amazon.
I earned my Ph.D. at Michigan State University supervised by Professor Xiaoming Liu.
My primary research interests lie in 3D Vision, encompassing monocular / multi-view depth estimation, camera calibration, image correspondence estimation, and two-view / multi-view camera pose estimation.
[Resume] [Google Scholar] [Linkedin] [Github]
2024
-
Revisit Self-supervised Depth Estimation with Local Structure-from-Motion
Shengjie Zhu, and Xiaoming Liu
In ECCV, 2024
-
RePLAy: Remove Projective LiDAR Depthmap Artifacts via Exploiting Epipolar Geometry
Shengjie* Zhu, Girish Chandar* Ganesan, Abhinav Kumar, and
1 more author
In ECCV, 2024
2023
-
Tame a Wild Camera: In-the-Wild Monocular Camera Calibration
Shengjie Zhu, Abhinav Kumar, Masa Hu, and
1 more author
In NeurIPS, 2023
-
LightedDepth: Video Depth Estimation in Light of Limited Inference View Angles
Shengjie Zhu, and Xiaoming Liu
In CVPR, 2023
-
PMatch: Paired Masked Image Modeling for Dense Geometric Matching
Shengjie Zhu, and Xiaoming Liu
In CVPR, 2023
2020
-
The edge of depth: Explicit constraints between segmentation and depth
Shengjie Zhu, Garrick Brazil, and Xiaoming Liu
In CVPR, 2020