Bowen Fu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bowen Fu has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Xiangyang Ji
Tsinghua University
4 shared publications - Chenyangguang Zhang
Tsinghua University
2 shared publications - Federico Tombari
Google, Zurich, Switzerland
2 shared publications - Gu Wang
Tsinghua University
2 shared publications - Yan Di
Technical University of Munich
2 shared publications - Fabian Manhardt
Google
1 shared publication
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (11) , 13159-13166
Fetch My Beer: Synthetic-to-Real Hierarchical Policy for Smooth Pick-and-Place
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (11) , 13159-13166
Fetch My Beer: Synthetic-to-Real Hierarchical Policy for Smooth Pick-and-Place
- 12 May 2025
- Published by Springer Nature
- p. 43-59
LanPose: Language-Instructed 6D Object Pose Estimation for Robotic Assembly
- 12 May 2025
- Published by Springer Nature
- p. 43-59
LanPose: Language-Instructed 6D Object Pose Estimation for Robotic Assembly
- 3 November 2024
- Published by Springer Nature
- p. 376-394
D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstruction
- 3 November 2024
- Published by Springer Nature
- p. 376-394
D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstruction
- 9 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (1) , 65-72
ROV6D: 6D Pose Estimation Benchmark Dataset for Underwater Remotely Operated Vehicles
Accurately localization between multi-robots is crucial for many underwater applications, such as tracking, convoying and subsea intervention tasks. 6D pose estimation is a fundamental task that enables precise object localization in 3D space with full six degrees of freedom. However, one critical challenge is the lack of available large-scale datasets due to the unbearable cost of labelled data collection. To overcome this difficulty, we propose a benchmark dataset, ROV6D, for 6D pose estimation of remotely operated vehicles (ROVs). The training subset consists of a large number of synthetic images with 6D pose ground truth for ROVs. These synthetic images are generated using BlenderProc and further rendered with the underwater neural rendering (UWNR) strategy to enhance their realism. The testing subsets cover different real-world scenarios, including the Pool subset and Maoming subset, focusing on challenging cases that involve partial occlusion and low visibility. Diverse recent methods are evaluated on the constructed dataset. The results show that methods based on dense coordinates currently perform best, outperforming both the keypoint-based method and the refinement-based method. Our dataset will be made publicly available soon.
- 9 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (1) , 65-72
ROV6D: 6D Pose Estimation Benchmark Dataset for Underwater Remotely Operated Vehicles
Accurately localization between multi-robots is crucial for many underwater applications, such as tracking, convoying and subsea intervention tasks. 6D pose estimation is a fundamental task that enables precise object localization in 3D space with full six degrees of freedom. However, one critical challenge is the lack of available large-scale datasets due to the unbearable cost of labelled data collection. To overcome this difficulty, we propose a benchmark dataset, ROV6D, for 6D pose estimation of remotely operated vehicles (ROVs). The training subset consists of a large number of synthetic images with 6D pose ground truth for ROVs. These synthetic images are generated using BlenderProc and further rendered with the underwater neural rendering (UWNR) strategy to enhance their realism. The testing subsets cover different real-world scenarios, including the Pool subset and Maoming subset, focusing on challenging cases that involve partial occlusion and low visibility. Diverse recent methods are evaluated on the constructed dataset. The results show that methods based on dense coordinates currently perform best, outperforming both the keypoint-based method and the refinement-based method. Our dataset will be made publicly available soon.