Yue Chen (陈悦)

I am a first-year PhD student at Westlake University and Zhejiang University, co-supervised by Yuliang Xiu and Gerard Pons-Moll.

Currently, I am working closely with Anpei Chen at Inception3D Lab, and have previously interned at Tencent AI Lab, working with Xuan Wang. I completed my M.S. at Xi'an Jiaotong University and my B.S. at Xiamen University.

Building a living world of magic where anyone can play, interact naturally, and feel as if they truly live there. As a Muggle dreaming of the Wizarding World, I feel so fortunate to create magic through what I am exploring on this journey.

alternative headshot
headshot
Research
GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstruction
Pradyumna YM, Yuxuan Xue†, Yue Chen, Nikita Kister, István Sárándi, Gerard Pons-Moll
arXiv, 2026

A feed-forward optimizer for human-scene interaction.

Human3R: Everyone Everywhere All at Once
Yue Chen, Xingyu Chen, Yuxuan Xue, Anpei Chen, Yuliang Xiu†, Gerard Pons-Moll
International Conference on Learning Representations (ICLR), 2026

Online human-scene reconstruction in one model, one stage.

TTT3R: 3D Reconstruction as Test-Time Training
Xingyu Chen, Yue Chen, Yuliang Xiu, Andreas Geiger, Anpei Chen†
International Conference on Learning Representations (ICLR), 2026

A simple state update rule to enhance length generalization for CUT3R.

🦣Easi3R: Estimating Disentangled Motion from DUSt3R Without Training
Xingyu Chen, Yue Chen, Yuliang Xiu, Andreas Geiger, Anpei Chen†
International Conference on Computer Vision (ICCV), 2025

A simple training-free approach adapting DUSt3R for dynamic scenes.

Feat2GS: Probing Visual Foundation Models with Gaussian Splatting
Yue Chen, Xingyu Chen, Anpei Chen, Gerard Pons-Moll, Yuliang Xiu†
Conference on Computer Vision and Pattern Recognition (CVPR), 2025

We found 2D metrics and 3D metrics are well-aligned.

L2G-NeRF: Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields
Yue Chen*, Xingyu Chen*⚑, Xuan Wang†, Qi Zhang, Yu Guo†, Ying Shan, Fei Wang
Conference on Computer Vision and Pattern Recognition (CVPR), 2023

Each ray is flexible but follows a single global rigid transformation.

UV Volumes for Real-time Rendering of Editable Free-view Human Performance
Yue Chen*, Xuan Wang*, Xingyu Chen, Qi Zhang, Xiaoyu Li, Yu Guo†, Jue Wang, Fei Wang
Conference on Computer Vision and Pattern Recognition (CVPR), 2023

Edit a dynamic human in NeRF with any texture you like.

PROCA: Place Recognition under Occlusion and Changing Appearance via Disentangled Representations
Yue Chen, Xingyu Chen†⚑, Yicen Li
International Conference on Robotics and Automation (ICRA), 2023

Disentangle images into place, appearance, and occlusion.

Ha-NeRF😆: Hallucinated Neural Radiance Fields in the Wild
Xingyu Chen, Qi Zhang†, Xiaoyu Li, Yue Chen, Ying Feng, Xuan Wang, Jue Wang
Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Visit the Brandenburg Gate in any season or weather.

🪄Created Magic

Making cool stuff is my jam — like rebuilding Hogwarts from Harry Potter movies or recreating lovely moments in 3D from my daily photos. 🖱️Click on the images below to render 3D, powered by Feat2GS.


template adapted from here and here