
Lu Sang
PhD StudentTechnical University of MunichSchool of Computation, Information and Technology
Informatics 9
Boltzmannstrasse 3
85748 Garching
Germany
Tel: +49-89-289-17782
Fax: +49-89-289-17757
Office: 02.09.055
Mail: lu.sang@in.tum.de
Brief Bio
I received my M.Sc. in Mathematics from the Technical University of Munich, and after that, I became a Ph.D. student in the Computer Vision Group, headed by Prof. Dr. Daniel Cremers at TUM.
My research interest is 3D reconstruction, photometric stereo, point cloud reconstruction, and geometry representation method.
Check out my home page for more project info: https://sangluisme.github.io/
Connect
Master Thesis / IDP / Guided Research
update 11.2023 Unfortunately all my thesis projects are occupied.
I offer the Master Thesis project on 3D reconstruction/camera tracking and mapping. If you are interested and fulfill the following requirements, please get in touch with me with your transcript.
- Good background in math;
- Practical Python or c++ programming skill;
- Have Attended at least one related CV course or seminar.
Publications
Export as PDF, XML, TEX or BIB
Preprints
2023
[] Weight-Aware Implicit Geometry Reconstruction with Curvature-Guided Sampling , In arXiv preprint arXiv:2306.02099, 2023.
Conference and Workshop Papers
2023
[] High-Quality RGB-D Reconstruction via Multi-View Uncalibrated Photometric Stereo and Gradient-SDF , In IEEE Winter Conference on Applications of Computer Vision (WACV), 2023. ([code] )
Spotlight Presentation
2022
[] Gradient-SDF: A Semi-Implicit Surface Representation for 3D Reconstruction , In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. ([poster] [presentation] [code])
2020
[] Inferring Super-Resolution Depth from a Moving Light-Source Enhanced RGB-D Sensor: A Variational Approach , In IEEE Winter Conference on Applications of Computer Vision (WACV), 2020. ([poster] [presentation] [code] [cvf])
Spotlight Presentation
Other Publications
2023
[] Coloring the Past: Neural Historical Buildings Reconstruction from Archival Photography , [paper], 2023. ([paper])
[] Erasing the Ephemeral: Joint Camera Refinement and Transient Object Removal for Street View Synthesis , [paper], 2023. ([paper])
Student Supervision
Successfully defended works:
Name | Project | Topic | Co-Supervisor |
---|---|---|---|
Sam Miao | Bachelor's Thesis | "Exploring the Differential Geometry from RGBD, point cloud and mesh data for Neural Surface Reconstruction" |