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.

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 Mixed Reality & 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.

My research interests lie in the interplay between computer vision and 3D geometry, with a focus on visual localization, 3D/4D reconstruction, and neural scene representations. I am also broadly interested in object-level perception, egocentric vision, and spatial computing.

Email  /  Google Scholar  /  Github  /  Linkedin

profile photo
News

[02-2024]    Our paper LEAP-VO is accepeted to CVPR 2024, see you in Seattle!
[02-2024]    Our paper NeRF-SCR is accepeted to ICRA 2024.
[10-2023]    I join Technical University of Munich as an ELLIS PhD student.
[08-2023]    I finish my Master's Thesis at Microsoft Mixed Reality & AI Lab Zurich.

Research
Results 2 for twoviewsfm
Results 1 for twoviewsfm
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.

Results 2 for twoviewsfm
Results 1 for twoviewsfm
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.

Results 2 for twoviewsfm
Results 1 for twoviewsfm
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.

Results 2 for twoviewsfm
Results 1 for twoviewsfm
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.

Cover Image for ACMMM
Cover Image for ACMMM
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.

Annimation for SCC
Cover Image for SCC
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
Results 2 for colmapslam
Results 1 for colmapslam
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.

Results 2 for pytorch3dvr
Results 1 for pytorch3dvr
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.

Results 2 for pytorch3dvr
Results 1 for pytorch3dvr
Pytorch3D VR Viewer
Research Assistant at ETH VLG
Supervised by Sergey Prokudin and Siyu Tang

Code

A customizable VR neural rendering viewer for evaluating and developing neural rendering methods in Python; built on Pytorch3D and OpenVR.

Experiences

Microsoft Mixed Reality & AI Lab Zurich Mentors: Rui Wang, Marc Pollefeys 11/2022 - 08/2023
ETH Computer Vision and Learning Group Mentors: Sergey Prokudin, Siyu Tang 06/2022 - 09/2022
SenseTime Research Mentors: Litong Feng, Wayne Zhang 05/2019 - 09/2019

Academic Services
  • Conference Reviewer: CVPR, ECCV, ICRA

Last updated: November 2024
Web page design credit to Jon Barron and Yuechen Zhang