Weirong Chen

Hi! I am a second-year PhD student at Technical University of Munich and University of Oxford under ELLIS, supervised by Prof. Daniel Cremers and Prof. Andrea Vedaldi. I also work closely with Dr. Chuanxia Zheng and Dr. Nikita Araslanov. I am currently a Student Researcher at Google Zurich.

Previously, I received my Master's degree in Computer Science from ETH Zurich advised by Prof. Marc Pollefeys. I worked on 3D vision projects at Microsoft Spatial AI Lab Zurich, Computer Vision and Geometry Group (CVG), and Computer Vision Lab (CVL). Before this, I obtained my Bachelor's degree in Computer Science from The Chinese University of Hong Kong and interned at SenseTime Research.

Email / Google Scholar / Github / Linkedin

News

[10-2025]    Back on Track has been selected as an award candidate at ICCV 2025.
[09-2025]    CoProU-VO received best paper award at GCPR 2025. Congrats to Jingchao and Oussema!
[06-2025]    Back on Track (dynamic SLAM with point tracking) was accepeted to ICCV 2025 (Oral).
[02-2025]    AnyCam (feed-forward VO trained with unlabled data) was accepeted to CVPR 2025.
[02-2024]    LEAP-VO (dynamic VO with point tracking) was accepeted to CVPR 2024.
[02-2024]    NeRF-SCR (NeRF-augmented visual localization) was accepeted to ICRA 2024.
[10-2023]    I joined Technical University of Munich as an ELLIS PhD student.

Research

My research interests lie at the intersection of computer vision and 3D geometry, with a focus on visual SLAM, 3D/4D reconstruction, and neural scene representations. I am also broadly interested in object-level perception, egocentric vision, and physical modeling.

	Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction Weirong Chen, Ganlin Zhang, Felix Wimbauer, Rui Wang, Nikita Araslanov, Andrea Vedaldi, Daniel Cremers International Conference on Computer Vision (ICCV), 2025 (Oral, Award Candidate) arXiv / Paper / Project Page / Code A method for consistent dynamic scene reconstruction via motion decoupling, bundle adjustment, and global refinement.
	CoProU-VO: Combining Projected Uncertainty for End-to-End Unsupervised Monocular Visual Odometry Jingchao Xie, Oussema Dhaouadi, Weirong Chen, Johannes Meier, Jacques Kaiser, Daniel Cremers German Conference on Pattern Recognition (GCPR), 2025 (Oral, Best Paper Award) arXiv / Project Page / Code An unsupervised visual odometry method that improves pose estimation in dynamic scenes.
	AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos Felix Wimbauer, Weirong Chen, Dominik Muhle, Christian Rupprecht, Daniel Cremers Computer Vision and Pattern Recognition Conference (CVPR), 2025 arXiv / Paper / Project Page / Code A method for learning camera poses and intrinsics from dynamic casual videos.
	DynSUP: Dynamic Gaussian Splatting from An Unposed Image Pair Weihang Li, Weirong Chen, Shenhan Qian, Jiajie Chen, Daniel Cremers, Haoang Li Preprint, 2024 arXiv / Project Page Dynamic radiance field reconstruction from only two images, enabled by object-level bundle adjustment.
	LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry Weirong Chen, Le Chen, Rui Wang, Marc Pollefeys Computer Vision and Pattern Recognition Conference (CVPR), 2024 arXiv / Project Page / Code / Video A robust visual odometry system leveraging temporal context with long-term point tracking to tackle occlusions and dynamic environments.
	Leveraging Neural Radiance Fields for Uncertainty-Aware Visual Localization Le Chen, Weirong Chen, Rui Wang, Marc Pollefeys International Conference on Robotics and Automation (ICRA), 2024 arXiv / Video A visual localization pipeline using rendered data from NeRF, uncertainty-guided novel view selection, and evidential scene coordinate regression.
	Uncertainty-Driven Dense Two-View Structure from Motion Weirong Chen, Suryansh Kumar, Fisher Yu International Conference on Intelligent Robots and Systems (IROS), 2023 IEEE Robotics and Automation Letters (RA-L), 2023 arXiv / Project Page / Video An accurate and reliable pipeline for dense two-view SfM using weighted bundle adjustment with robust outlier filtering and learning-based confidence modeling.
	Webly Supervised Image Classification with Metadata: Automatic Noisy Label Correction via Visual-Semantic Graph Jingkang Yang, Weirong Chen*, Litong Feng, Xiaopeng Yan, Huabin Zheng, Wayne Zhang ACM International Conference on Multimedia (ACM MM), 2020 (Oral)* arXiv / Slides Webly supervised learning for semantic label confusion using visual-semantic graph with metadata-aware anchor selection and GNN-based label propagation.
	Webly Supervised Image Classification with Self-Contained Confidence Jingkang Yang, Litong Feng, Weirong Chen, Xiaopeng Yan, Huabin Zheng, Ping Luo, Wayne Zhang European Conference on Computer Vision (ECCV), 2020 arXiv / Code Webly supervised learning for noisy label classification via sample-wise web label correction with model confidence and pseudo machine label.

Other Projects

An Efficient and Accurate Offline Python SLAM using COLMAP
Conference with Yifei Liu, Kexin Shi, Yidan Gao
Supervised by Paul‑Edouard Sarlin and Marc Pollefeys

Demo (KITTI) / Demo (Zurich) / Report

A robust and highly-extensible Python SLAM built on pycolmap; achieved better pose accuracy and significant speed improvement compared to COLMAP.

Real-time Photorealistic Neural Rendering in VR
with Shengqu Cai, Mingyang Song, Tianfu Wang
Supervised by Sergey Prokudin

Demo / Report / Code

A general neural rendering pipeline for photorealistic synthesis in VR devices in real-time; demo included human neural rendering and scene style transfer.

Experiences

Microsoft Mixed Reality & AI Lab Zurich	Mentors: Rui Wang, Marc Pollefeys	11/2022 - 08/2023
ETH Computer Vision and Geometry Group	Mentors: Songyou Peng, Marc Pollefeys	02/2021 - 08/2021
SenseTime Research	Mentors: Litong Feng, Wayne Zhang	05/2019 - 09/2019

Academic Services

Conference Reviewer: CVPR, ECCV, ICCV, ICRA, IROS

Last updated: Oct 2025
Web page design credit to Jon Barron and Yuechen Zhang