About Me

I am a PhD researcher at Technical University of Munich(TUM), specializing in 3D vision for scene understanding, reconstruction, and object pose estimation/tracking, enabling models to generalize to novel scenes through multi-modal training, test-time adaptation, and efficient training or fine-tuning of foundation models, with applications in AR/VR, robotics, and autonomous driving. I am currently working with Prof. Nassir Navab, PD Dr. Slobodan Ilic and Prof. Benjamin Busam. I also work closely with Dr.Peter KT Yu, founder of XYZ Robotics.

Research Interests

  • 3D Scene Understanding & Reconstruction
  • Vision for Robotic Manipulation
  • Multi-modal representation Learning
  • Open-Vocabulary Vision Systems

Professional Activities


Co-organized Workshops and Challenges


Reviewing

  • Conference Reviewer: CVPR, ECCV, ICCV, NeurIPS
  • Journal Reviewer: IEEE T-PAMI, IJCV, IEEE RA-L

Teaching Assistant

  • Introduction to Deep Learning(IN22346), TUM, WS 2021/2022
  • Introduction to Deep Learning(IN22346), TUM, WS WS 2022/2023
  • Praktikum on 3D Computer Vision (IN2106, IN4313), TUM, WS 2023/2024
  • Master-Seminar - Modern Computer Vision Methods (IN2107, IN4486), TUM, WS 2023/2024
  • Bachelor-Praktikum - Foundations in 3D Computer Vision (IN0012), TUM, SS 2024
  • Master-Praktikum - Advanced Topics in 3D Computer Vision (IN2106, IN4023), TUM, SS 2024
  • Master-Seminar - Modern Computer Vision Methods (IN2107, IN4486), TUM, WS 2024/2025
  • Praktikum on 3D Computer Vision (IN2106, IN4313), TUM, WS 2024/2025
  • Master-Praktikum - Advanced Topics in 3D Computer Vision (IN2106, IN4023), TUM, SS 2025

Selected Publications

xyz-ibd teaser
XYZ-IBD: A High-precision Bin-picking Dataset for Object 6D Pose Estimation Capturing Real-world Industrial Complexity

Junwen Huang, Jizhong Liang, Jiaqi Hu, Martin Sundermeyer, Peter KT Yu, Nassir Navab, Benjamin Busam

Arixv 2025

raypose teaser
RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation

Junwen Huang, Shishir Reddy Vutukur, Peter KT Yu, Nassir Navab, Slobodan Ilic, Benjamin Busam

ICCV 2025

ttapose teaser
TTAPose: Test-Time Adaptation for Unseen Object Pose Estimation

Junwen Huang, Peter KT Yu, Nassir Navab, Benjamin Busam

IEEE RA-L 2025

GCE-Pose teaser
GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimation

*Weihang Li, *Hongli Xu, *Junwen Huang, *Hyunjun Jung, Peter KT Yu, Nassir Navab, Benjamin Busam

(* Joint first authors)

CVPR 2025

Alignist teaser
Alignist: CAD-Informed Orientation Distribution Estimation by Fusing Shape and Correspondences

Shishir Reddy Vutukur, Rasmus Laurvig Haugaard, Junwen Huang, Benjamin Busam, Tolga Birdal

ECCV 2024

MatchU teaser
MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images

Junwen Huang, Hao Yu, Kuan-Ting Yu, Nassir Navab, Slobodan Ilic, Benjamin Busam

CVPR 2024

SSR-2D teaser
SSR-2D: Semantic 3D Scene Reconstruction from 2D Images

Junwen Huang, Alexey Artemov, Yujin Chen, Shuaifeng Zhi, Kai Xu, Matthias Nießner

IEEE TPAMI 2024

StablePose teaser
StablePose: Learning 6D Object Poses from Geometrically Stable Patches

*Yifei Shi, *Junwen Huang, Xin Xu, Yifan Zhang, Kai Xu

(* Joint first authors)

CVPR 2021

SymmetryNet teaser
SymmetryNet: Learning to Predict Reflectional and Rotational Symmetries of 3D Shapes from Single-View RGB-D Images

Yifei Shi, Junwen Huang, Hongjia Zhang, Xin Xu, Szymon Rusinkiewicz, Kai Xu

ACM TOG 2020

Supervised Student Projects


  • Weihang Li and Hongli Xu: GCE-Pose (CVPR25)
  • Emrah Dogan: Joint Optimization of Segmentation and Pose Estimation (ongoing)
  • Jiaqi Hu: Anything 6D: Generative Semantic Prior for 6D Pose Estimation (ongoing)
  • Hongli Xu: ArticGS: Articulated Object GS-Reconstruction (ongoing)
  • Cuong Van Dam: Unseen Object Segmentation for Industrial Bin-picking (finished)
  • Haoqing Wu: 6-DoF Pose Estimation with Diffusion Models (finished)