![]() |
Bowen WenI am a Senior Research Scientist at NVIDIA Research. My research areas include robotic perception, computer vision. More recently, I focus on large foundation models for 3D visual perception and learning to facilitate robotics or embodied AI. My two leading projects received the best paper award nomination at CVPR 2025 and RSS 2022. I obtained my PhD degree in Computer Science from Rutgers University in 2022, advised by Prof. Kostas Bekris. During my PhD, I've spent wonderful summers with Google[X], Meta Reality Labs, Amazon Lab 126 and SenseTime working as a research intern. Prior to my PhD, I obtained MS degree from Ohio State University in 2018 and BS degree from Xi'an Jiaotong University in 2016.Email: wenbowenxjtu [at] gmail [dot] com Research Interests: Robotics, Computer Vision, Artificial Intelligence |
I'm always looking for self-motivated research interns and open to university collaborations. Please drop me a line if you are interested!
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
FoundationStereo: Zero-Shot Stereo Matching
CVPR 2025 (🏆 Best Paper Nomination)
[pdf]
[code]
[project page]
|
![]() |
FoundationPose: Unified 6d pose estimation and tracking of novel objects
CVPR 2024 (Highlight)
[pdf]
[code]
[project page]
|
![]() |
BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
CVPR 2023
[pdf]
[code]
[project page]
[video]
|
MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations
CoRL 2023
[pdf]
[code]
[project page]
|
|
![]() |
CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulation
ICRA 2022
[pdf]
[code]
[video]
|
![]() |
BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models
IROS 2021
[pdf]
[code]
[presentation video]
[supplementary video]
|
![]() |
se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains
IROS 2020
[pdf]
[code]
[supplementary video]
[presentation video]
|
![]() |
Any6D: Model-free 6D Pose Estimation of Novel Objects
CVPR 2025
[pdf]
[code]
[project page]
|
![]() |
SPOT: SE(3) Pose Trajectory Diffusion for Object-Centric Manipulation
ICRA 2025
[pdf]
[code]
[project page]
|
![]() |
Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects
CVPR 2024
[pdf]
[code]
[project page]
|
![]() |
AutoMate: Specialist and Generalist Assembly Policies over Diverse Geometries
RSS 2024
[pdf]
[code]
[project page]
|
SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment
CoRL 2024
[pdf]
[project page]
|
|
![]() |
You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration
RSS 2022 (🏆 Best Paper Nomination)
[pdf]
[code of tracking]
[code of grasping]
[video]
|
![]() |
Complex In-Hand Manipulation via Compliance-Enabled Finger Gaiting and Multi-Modal Planning
IEEE Robotics and Automation Letters 2022
[pdf]
[video]
[news
coverage]
|
![]() |
Learning Sensorimotor Primitives of Sequential Manipulation Tasks from Visual Demonstrations
ICRA 2022
[pdf]
[video]
|
![]() |
Vision-driven Compliant Manipulation for Reliable, High-Precision Assembly Tasks
RSS 2021
[pdf] [video] |
![]() |
Task-driven Perception and Manipulation for Constrained Placement with No Shape Priors
RA-L and IROS 2020
[pdf]
[video]
|
![]() |
Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Hands
IEEE International Conference on Robotics and Automation (ICRA) 2020
[pdf]
[code]
[video]
|
©Bowen Wen. All rights reserved