Shuai Chen

I am a 4th year PhD student in Active Vision Laboratory at University of Oxford, supervised by Prof. Victor Prisacariu. I received my Master and Bachelor in Electrical Engineering at the University of Southern California.

Previously, I was a senior AI algorithm engineer and a team leader at Huawei Technologies, where I led several commercially successful computer vision and computational photography projects in Huawei/Honor flagship smartphones.

I spent a delightful time at Niantic Labs as a research intern, mentored by amazing scientists Eric Brachmann, Tommaso Cavallari, and Victor Prisacariu.

Recently, I joined Meta Reality Lab as a research scientist intern.

Email  /  CV  /  Google Scholar  /  LinkedIn  /  Github

profile photo
Research

I'm interested in 3D Vision, Computational Photography, and Genarative AI.







GSLoc: Efficient Camera Pose Refinement via 3D Gaussian Splatting
Changkun Liu, Shuai Chen, Yash Bhalgat, Siyan Hu, Zirui Wang, Ming Cheng, Victor Prisacariu, Tristan Braud
arXiv, 2024
paper

Efficient camera pose refinement using 3D Gaussian Splatting and 3D foundation model.

When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models
Xianzheng Ma*, Yash Bhalgat*, Brandon Smart*, Shuai Chen, Xinghui Li, Jian Ding, Jindong Gu, Dave Zhenyu Chen, Songyou Peng, Jiawang Bian, Philip Torr, Marc Pollefeys, Matthias Nießner, Ian D Reid, Angel X. Chang, Iro Laina, Victor Prisacariu
arXiv, 2024
paper

A survey paper that provides a comprehensive overview of the methodologies enabling LLMs to process, understand, and generate 3D data.

Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer
Eric Brachmann, Jamie Wynn, Shuai Chen, Tommaso Cavallari, Áron Monszpart, Daniyar Turmukhambetov, Victor Prisacariu
ECCV, 2024   (Oral)
project page / paper / code

A novel learning-based structure-from-motion (SfM) method using scene coordinate regression.

Map-Relative Pose Regression for Visual Re-Localization
Shuai Chen, Tommaso Cavallari, Victor Prisacariu, Eric Brachmann
CVPR, 2024   (Highlight)
project page / paper / code

A scene-agnostic pose regression network that maps scene-specific representations to 6-DoF camera poses, enabling APRs to adapt to new scenes in 5 minutes.

Neural Refinement for Absolute Pose Regression with Feature Synthesis
Shuai Chen, Yash Bhalgat, Xinghui Li, Jiawang Bian, Kejie Li, Zirui Wang, Victor Prisacariu
CVPR, 2024
project page / paper / code

A post-process for refining generic APRs using neural feature fields.

HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisation
Changkun Liu, Shuai Chen, Yukun Zhao, Huajian Huang, Victor Prisacariu, Tristan Braud
ICRA, 2024
project page / paper / code

An APR-agnostic framework that accelerates pose refinement via pose-retrieval and uncertainty estimation.

DFNet: Enhance Absolute Pose Regression with Direct Feature Matching
Shuai Chen, Xinghui Li, Zirui Wang, Victor Prisacariu
ECCV, 2022
project page / paper / code

Leveraging luma-prior NeRF and direct feature matching to enhance 6-DoF camera pose regression approaches.

Deep Online Video Stabilization using IMU Sensors
Chen Li, Li Song, Shuai Chen, Rong Xie, Wenjun Zhang,
IEEE Transactions on Multimedia, 2022
paper

Real-time and data driven video stabilization using IMU sensors.

Direct-PoseNet: Absolute Pose Regression with Photometric Consistency
Shuai Chen, Zirui Wang, Victor Prisacariu
3DV, 2021
project page / paper / code

6-DoF camera pose regression with NeRF-based differentiable renderer.


Academic Services

Reviewer ECCV 2022,24, CVPR 2023,24, ICCV 2023, ICRA 2024, RA-L 2024


Website template borrowed from Jon Barron.