I'm a research scientist at Huawei Darwin Research Center (London).
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.
I am looking for prospective interns to work on 3D/4D/VLM stuff.
Feel free to drop an email if you are interested in working with me.
Latest News
๐Feb 2026I rejected the request for serving as a reviewer of
NeurIPS 2026!
๐Feb 2026Paper on Scaling up 3D data for foundation model
training accepted at CVPR 2026!
๐จโ๐Sep 2025Successfully defended my PhD thesis! ๐
๐Sep 2025Paper on 3D geometric foundation models for Gaussian
Splatting accepted at NeurIPS 2025!
๐Aug 2023Received the Research Achievement Award at SoC | NUS! ๐
๐Jul 2023Paper on registering neural radiance fields accepted
at ICCV 2023!
๐Jan 2023Paper on neural radiance fields accepted at CVPR 2023!
๐Jan 2023Paper on large scale Structure-from-Motion accepted
at ICRA 2023!
๐จโ๐Jan 2022Joined the CVRP lab at NUS as a PhD student!
๐May 2021Paper on rotation averaging accepted at CVPR 2021!
๐July 2020Paper on large-scale SfM accepted at Pattern Recognition 2020!
Publications
Hover or tap the lightbulb beside author names to see the main idea 10 publications
CVPR 2026
FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation
Chenhan Jiang*, Yu Chen*, Qingwen Zhang,
Jifei Song, Songcen Xu, Dit-Yan Yeung, Jiankang Deng ๐ก* Equal contributionFreeScale turns sparse real-world captures into a scalable 3D data engine
by sampling certainty-aware free views from reconstructed scenes and using them to improve
feed-forward NVS and per-scene 3DGS.
DReg-NeRF: Deep Registration for Neural Radiance Fields
Yu Chen, Gim Hee Lee ๐กGiven NeRF blocks in different coordinate systems, DReg-NeRF registers
them together end-to-end using 3D FPN and transformers on occupancy grids.
DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields
Yu Chen, Gim Hee Lee ๐กDBARF jointly optimizes generalizable NeRF and camera poses without pose
initialization by constructing residual maps from feature extraction.
AdaSfM: From Coarse Global to Fine Incremental Adaptive Structure from Motion
Yu Chen, Zihao Yu, Shu Song, Tianning Yu, Jianming Li, Gim Hee Lee
๐กAdaSfM adopts a coarse-to-fine strategy for SfM, using coarse global
reconstruction to provide priors for local incremental reconstruction in a distributed way.
Hybrid Rotation Averaging: A Fast and Robust Rotation Averaging Approach
Yu Chen, Ji Zhao, Laurent Kneip ๐กHybrid 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.
