Bowen Wen | Research

Bowen Wen

I am a Senior Research Scientist at NVIDIA Research. My research areas include robotic perception, computer vision. Specifically, I work on 3D visual perception and learning to facilitate robotic manipulations. 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], Facebook Reality Labs, Amazon Lab 126 and SenseTime working as a research intern. Previously, I obtained MS degree in ECE from Ohio State University in 2018 and BS degree in Energy and Automation from Xi'an Jiaotong University in 2016. Personal page: https://wenbowen123.github.io/

Research Area(s)

Computer Vision

VR, AR and Display Technology

Main Field of Interest

Computer Vision

Google Scholar

https://scholar.google.com/citations?user=VSG7Z0kAAAAJ&hl=en&oi=ao

Publications

2025

RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion

Bardienus P. Duisterhof, Jan Oberst, Bowen Wen, Stan Birchfield, Deva Ramanan, Jeffrey Ichnowski

FoundationStereo: Zero-Shot Stereo Matching

Bowen Wen, Matthew Trepte, Joseph Aribido, Jan Kautz, Orazio Gallo, Stan Birchfield

Best Paper Nomination

SPOT: SE(3) Pose Trajectory Diffusion for Object-Centric Manipulation

Cheng-Chun Hsu, Bowen Wen, Jie Xu, Yashraj Narang, , Yuke Zhu, Joydeep Biswas, Stan Birchfield

2024

SkillGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment

Caelan Garrett, Ajay Mandlekar, Bowen Wen, Dieter Fox

Conference on Robot Learning (CoRL)

FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

Bowen Wen, Wei Yang, Jan Kautz, Stan Birchfield

NeRFDeformer: NeRF Transformation from a Single View via 3D Scene Flows

Zhenggang Tang, Zhongzheng Ren, Xiaoming Zhao, Bowen Wen, Jonathan Tremblay, Stan Birchfield, Alexander Schwing

Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects

Yijia Weng, Bowen Wen, Jonathan Tremblay, Valts Blukis, Dieter Fox, Leo Guibas, Stan Birchfield

2023

HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructions

Andrew Guo, Bowen Wen, Jianhe Yuan, Jonathan Tremblay, Stephen Tyree, Jeff Smith, Stan Birchfield

TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation

Taeyeop Lee, Jonathan Tremblay, Valts Blukis, Bowen Wen, Byeong-Uk Lee, Inkyu Shin, Stan Birchfield, In So Kweon, Kuk-Jin Yoon

BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects

Bowen Wen, Jonathan Tremblay, Valts Blukis, Stephen Tyree, Thomas Müller, Alex Evans, Dieter Fox, Jan Kautz, Stan Birchfield

Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation

Yunzhi Lin, Thomas Müller, Jonathan Tremblay, Bowen Wen, Stephen Tyree, Alex Evans, Patricio A. Vela, Stan Birchfield

RGB-Only Reconstruction of Tabletop Scenes for Collision-Free Manipulator Control

Zhenggang Tang, Balakumar Sundaralingam, Jonathan Tremblay, Bowen Wen, Ye Yuan, Stephen Tyree, Charles Loop, Alexander Schwing, Stan Birchfield