Navigation

Sicong Pan

Ph.D. Student

	Contact
	Email :	span_at_uni-bonn.de pan_at_cs.uni-bonn.de
	Phone :	+49(0)228 73-54154
	Address:	Sicong Pan Rheinische Friedrich-Willhelms-Universität Bonn Institut für Informatik VI Room 2.108 Friedrich-Hirzebruch-Allee 8 53115 Bonn Germany

About Me

I am a Ph.D. student at the Humanoid Robots Lab headed by Maren Bennewitz at the University of Bonn. I received my master's degree in Computer Science from Fudan University in 2022.

Brief CV

since 02.2023	Ph.D. student at the Humanoid Robots Lab
09.2018 - 01.2022	M.Sc. in Computer Science, Fudan University, China
09.2014 - 07.2018	B.Eng. in Computer Science, Shanghai University, China

Research Interests

3D Object Reconstruciton
View Planning
Deep Learning and Coverage Optimization

Current Research Projects

Automation and Artificial Intelligence for Monitoring and Decision Making in Horticultural Crops (AID4Crops)

Publications

How Many Views Are Needed to Reconstruct an Unknown Object Using NeRF? (Video). Sicong Pan, Liren Jin, Hao Hu, Marija Popović, and Maren Bennewitz. (*equal contribution) ArXiv preprint, submitted for publication. Code available!
Active Implicit Reconstruction using One-Shot View Planning (Video). Hao Hu, Sicong Pan, Liren Jin, Marija Popović, and Maren Bennewitz. (*equal contribution) ArXiv preprint, submitted for publication.
One-Shot View Planning for Fast and Complete Unknown Object Reconstruction (Video). Sicong Pan, Hao Hu, Hui Wei, Nils Dengler, Tobias Zaenker, and Maren Bennewitz. ArXiv preprint, submitted for publication. Code available!
A Global Generalized Maximum Coverage-based Solution to the Non-model-based View Planning Problem for Object Reconstruction (Video). Sicong Pan and Hui Wei. In: Computer Vision and Image Understanding (CVIU), 2023. Code available!
SCVP: Learning One-Shot View Planning via Set Covering for Unknown Object Reconstruction (Video). Sicong Pan, Hao Hu, and Hui Wei. In: IEEE Robotics and Automation Letters (RA-L), 2022. Code and Presentation (ICRA 2022) available!
A Global Max-Flow-Based Multi-Resolution Next-Best-View Method for Reconstruction of 3D Unknown Objects (Video). Sicong Pan and Hui Wei. In: IEEE Robotics and Automation Letters (RA-L), 2022. Code and Presentation (ICRA 2023) available!