profile photo

Shuai Chen

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

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

I also interned at Niantic Labs and Meta Reality Lab as a research scientist intern.

In 2025, I joined Niantic as a senior research scientist.

Research

I’m interested in 3D Vision, Computational Photography, and Generative AI.

GS-CPR
GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting
Changkun Liu, Shuai Chen, Yash Bhalgat, Siyan Hu, Zirui Wang, Ming Cheng, Victor Prisacariu, Tristan Braud
ICLR, 2025
project page / paper / code

Efficient camera pose refinement using 3D Gaussian Splatting and 3D foundation model MASt3R.

LLM_3D
LLM_3D
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.

ACE Zero
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 (2.3%)
project page / paper / code

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

MARePo
Map-Relative Pose Regression for Visual Re-Localization
Shuai Chen, Tommaso Cavallari, Victor Prisacariu, Eric Brachmann
CVPR, 2024   Highlight (11.9%)
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.

NeFeS
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
HR-APR
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
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.

DOVS
DOVS
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
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, 2024; CVPR 2023, 2024; ICCV 2023, 2025; ICRA 2024; RA-L 2024, 2025; NeurIPS 2025