Chen Yu

Chen Yu

Research Scientist @ London
NUS VLM 3DGS NeRF SfM&SLAM 3D Generation

I obtained my doctoral degree at the National University of Singapore (NUS) under the guidance of Prof. Gim Hee Lee, supported by a Google PhD Fellowship. My academic journey began with an M.S. in Computer Science at Peking University, working with Prof. Yisong Chen and Prof. Shuhan Shen, and a B.E. in Software Engineering from Beihang University.

Latest News

๐Ÿ˜Ž Feb 2026 Paper on Scaling up 3D data for foundation model training accepted at CVPR 2026!
๐Ÿ‘จโ€๐ŸŽ“ Sep 2025 Successfully defended my PhD thesis! ๐ŸŽ‰
๐Ÿ˜Ž Sep 2025 Paper on 3D geometric foundation models for Gaussian Splatting accepted at NeurIPS 2025!
๐Ÿš€ Jan 2025 Received the Research Achievement Award at SoC | NUS!
๐Ÿš€ Sep 2024 Received the Chinese Government Award for Outstanding Self-Financed Students Abroad! ๐ŸŽ‰
๐Ÿ˜Ž Sep 2024 Paper on distributed large-scale 3D Gaussian Splatting accepted at NeurIPS 2024!
๐Ÿ˜Ž May 2024 Invited talk at 3D CVer on distributed 3D Gaussian Splatting!
๐Ÿ˜Ž Feb 2024 Paper on anti-aliasing 3D Gaussian Splatting accepted at CVPR 2024!
๐Ÿš€ Jan 2024 Awarded the Dean's Graduate Research Achievement Award at NUS! ๐ŸŽ‰
๐Ÿš€ Nov 2023 Awarded the Google PhD Fellowship 2023 in Machine Perception! ๐ŸŽ‰
๐Ÿš€ Aug 2023 Received the Research Achievement Award at SoC | NUS! ๐ŸŽ‰
๐Ÿ˜Ž Jul 2023 Paper on registering neural radiance fields accepted at ICCV 2023!
๐Ÿ˜Ž Jan 2023 Paper on neural radiance fields accepted at CVPR 2023!
๐Ÿ˜Ž Jan 2023 Paper on large scale Structure-from-Motion accepted at ICRA 2023!
๐Ÿ‘จโ€๐ŸŽ“ Jan 2022 Joined the CVRP lab at NUS as a PhD student!
๐Ÿ˜Ž May 2021 Paper on rotation averaging accepted at CVPR 2021!
๐Ÿ˜Ž July 2020 Paper on large-scale SfM accepted at Pattern Recognition 2020!

Publications

Hover over the ๐Ÿ’ก icon next to author names to see the main idea for paper summaries
PhD Thesis 2025 PhD Thesis

Large-Scale Neural 3D Scene Reconstruction, Rendering, and Beyond

Yu Chen
Paper Slides Cite
NeurIPS 2025 DeepGfM

Deep Gaussian from Motion: Exploring 3D Geometric Foundation Models for Gaussian Splatting

Yu Chen, Rolandos Alexandros Potamias, Evangelos Ververas, Jifei Song, Jiankang Deng, Gim Hee Lee
Paper Web Code Cite
NeurIPS 2024 DOGS

DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus

Yu Chen, Gim Hee Lee
Paper Web Code Poster Cite
CVPR 2024 MS-GS

Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering

Zhiwen Yan, Weng Fei Low, Yu Chen, Gim Hee Lee
Paper Web Code Cite
ICCV 2023 DReg-NeRF

DReg-NeRF: Deep Registration for Neural Radiance Fields

Yu Chen, Gim Hee Lee ๐Ÿ’ก Given NeRF blocks in different coordinate systems, DReg-NeRF registers them together end-to-end using 3D FPN and transformers on occupancy grids.
Paper Web Code Poster Data Cite
CVPR 2023 DBARF

DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields

Yu Chen, Gim Hee Lee ๐Ÿ’ก DBARF jointly optimizes generalizable NeRF and camera poses without pose initialization by constructing residual maps from feature extraction.
Paper Web Code Poster Cite
ICRA 2023 AdaSfM

AdaSfM: From Coarse Global to Fine Incremental Adaptive Structure from Motion

Yu Chen, Zihao Yu, Shu Song, Tianning Yu, Jianming Li, Gim Hee Lee ๐Ÿ’ก AdaSfM adopts a coarse-to-fine strategy for SfM, using coarse global reconstruction to provide priors for local incremental reconstruction in a distributed way.
Paper Web Code Poster Cite
CVPR 2021 Hybrid Rotation Averaging

Hybrid Rotation Averaging: A Fast and Robust Rotation Averaging Approach

Yu Chen, Ji Zhao, Laurent Kneip ๐Ÿ’ก Hybrid rotation averaging combines global and local methods, enhancing robustness by pre-filtering wrong edges in triplets and using global rotations as priors for incremental SfM.
Paper Code Cite
Pattern Recognition 2020 GraphSfM

Graph-Based Parallel Large Scale Structure from Motion

Yu Chen, Shuhan Shen, Yisong Chen, Guoping Wang ๐Ÿ’ก GraphSfM splits and stitches scenes based on graph connectivity, enabling efficient distributed large-scale reconstruction. First open-source distributed SfM implementation.
Paper Code Cite

Awards & Honors

๐ŸŽ Jan 2024 Dean's Graduate Research Achievement Award, SoC, NUS
๐ŸŽ Nov 2023 Google PhD Fellowship 2023
๐ŸŽ Aug 2023 Research Achievement Award, SoC, NUS
๐Ÿ† Aug 2021 Rising Star in the Quarter, Segway Robotics
๐Ÿฅˆ Nov 2019 2nd Place in 3D Reconstruction Track, China VR Innovation Challenge
๐Ÿ… Apr 2018 2nd Place in 3v3 Basketball, Peking University
๐Ÿ† Mar 2014 Top Ten Broadcasting Hosts, BUAA
๐Ÿฅ‡ Nov 2013 Champion in Speech Contest, School of Software, BUAA

Experience

SLAM Algorithm Engineer
Segway Robotics โ€ข Jul 2020 - Dec 2021
Visual-Inertial-Odometry SLAM, Marker SLAM, Outdoor Multi-sensor Fusion SfM
Algorithm Intern
Segway Robotics โ€ข Apr 2020 - Jun 2020
Visual-Inertial SLAM, Self-Calibration on scooters (with Jianming Li)
Research Intern
TuSimple โ€ข Apr 2019 - Jul 2019
High-Definition mapping, Rotation Averaging (with Dr. Ji Zhao)
Algorithm Intern
Megvii Research โ€ข Sep 2018 - Dec 2018
Real-time 3D reconstruction, texture mapping