Boyang Sun (孙柏扬)

I am a Computer Science PhD student at the Computer Vision and Geometry Group, at ETH Zurich, under the supervision of Prof. Marc Pollefeys. My reaseach focuses on Robotics and Computer Vision. I also work closely with Prof. Hermann Blum and Dr. Cesar Cadena.

I obtained my Master degree in Robotics, Systems and Control from Department of Mechanical Engineering at ETH Zurich, where I spent time at Autonomous Systems Lab, under the supervision of Prof. Roland Siegwart.

In my free time, I enjoy watching movies, traveling and doing sports. I also play guitar with Zurich Drift.

Email / GitHub / Google Scholar / LinkedIn

News

02/2026 Loop Closure from Two Views (2GO) is accepted to RA-L!
02/2026 Sight over Site is accepted to ICRA 2026!
10/2025 Our RA-L paper, FrontierNet and its extension OpenFrontier will be presented at IROS 2025!
08/2025 ActLoc is accepted to CoRL 2025!
06/2025 We will organize the Active Perception Workshop at IROS 2025!
06/2025 SuperDec is accepted to ICCV 2025 (Oral)!
05/2025 FrontierNet is accepted to RA-L 2025!
05/2025 ForesightNav is accepted to CVPR'W 2025!
03/2025 VidBot is accepted to CVPR 2025!
07/2024 Learning Where to Look is accepted to ECCV 2024!
03/2024 I served as a Technical Chair at 3DV 2024!
03/2024 NeRF On-the-go is accepted to CVPR 2024!
01/2024 Multi-agent Active Visual Localization is accepted at ICRA 2024!
01/2024 MR for Human-robot Teaming is accepted at ICRA 2024!
09/2023 See Yourself in Others received Best Paper at IROS 2023 WS!

Research

	Sight Over Site: Perception-Aware Reinforcement Learning for Efficient Robotic Inspection Richard Kuhlmann, Jakob Wolfram, Boyang Sun, Jiaxu Xing, Davide Scaramuzza, Marc Pollefeys, Cesar Cadena ICRA 2026 paper / code / website / video /
	Loop Closure from Two Views: Revisiting PGO for Scalable Trajectory Estimation through Monocular Priors Tian Yi Lim, Boyang Sun, Marc Pollefeys, Hermann Blum RA-L 2026* paper / code / website /
	What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified FrameworK Hongze Wang, Boyang Sun, Jiaxu Xing, Fan Yang, Marco Hutter, Dhruv Shah, Davide Scaramuzza, Marc Pollefeys Preprint 2025 paper / code / website / video /
	ActLoc: Learning to Localize on the Move via Active Viewpoint Selection Jiajie Li, Boyang Sun, Luca Di Giammarino, Hermann Blum, Marc Pollefeys CoRL 2025 paper / code / website / video /
	FrontierNet: Learning Visual Cues to Explore Boyang Sun, Hanzhi Chen, Stefan Leutenegger, Cesar Cadena, Marc Pollefeys, Hermann Blum RA-L 2025 paper / IEEE / code / website / video /
	SuperDec: 3D Scene Decomposition with Superquadric Primitives Elisabetta Fedele, Boyang Sun, Leonidas Guibas, Marc Pollefeys, Francis Engelmann ICCV 2025(Oral) paper / code / website / video /
	VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation Hanzhi Chen, Boyang Sun, Anran Zhang, Marc Pollefeys, Stefan Leutenegger CVPR 2025 paper / code / website / video /
	ForesightNav: Learning Scene Imagination for Efficient Exploration Hardik Shah, Jiaxu Xing, Nico Messikommer, Boyang Sun, Marc Pollefeys, Davide Scaramuzza CVPRW 2025 paper / code / website /
	Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization Using Geometrical Information Luca Di Giammarino, Boyang Sun, Giorgio Grisetti, Marc Pollefeys, Hermann Blum, Daniel Barath ECCV 2024 paper / code / video /
	NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild Weining Ren, Zihan Zhu, Boyang Sun, Jiaqi Chen, Marc Pollefeys, Songyou Peng CVPR 2024 paper / code / website /
	Active visual localization for multi-agent collaboration: A data-driven approach Boyang Sun, Matthew Hanlon, Marc Pollefeys, Hermann Blum ICRA 2024 paper / IEEE / poster /
	A 3d mixed reality interface for human-robot teaming Boyang Sun, Jiaqi Chen, Marc Pollefeys, Hermann Blum ICRA 2024 paper / IEEE / code / video /
	See yourself in others: Attending multiple tasks for own failure detection Boyang Sun, Jiaxu Xing, Hermann Blum, Roland Siegwart, Cesar Cadena ICRA 2022 paper / IEEE /