Yue Chen (陈悦)

I obtained my Master’s degree from the Institute of Artificial Intelligence and Robotics at Xi’an Jiaotong University in 2022, supervised by Prof. Fei Wang and Prof.Yu Guo. I did my undergrad at Xiamen University.

During my master, I was a research intern in Visual Computing Center at Tencent AI lab, working with Jue Wang and Xuan Wang.

I am a Muggle dreaming of the Wizarding World. Luckily, I can create magic via neural fields and a closed loop formed by computer vision and computer graphics between 2D images and the 3D world!

Email  |  Google Scholar  |  GitHub

headshot
News
  • 03/2023 I am actively looking for a Ph.D. position. If possible, please email me for further communication!
  • 02/2023 2 papers (L2G-NeRF, UV Volumes) accepted to CVPR 2023!
  • 01/2023 1 paper (PROCA) accepted to ICRA 2023!
  • 03/2022 1 paper (Ha-NeRF) accepted to CVPR 2022!
Research

Equal Contribution * , Corresponding Author †

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
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
project page / arXiv / code / video

A Local-to-Global robust registration strategy for bundle-adjusting Neural Radiance Fields, combining the global and local alignment via differentiable parameter estimation.

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
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
project page / arXiv / code / supplementary / video

The first deformable, real-time rendering, and editable NeRF, decomposing a dynamic human into 3D UV Volumes and a 2D appearance texture.

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

An unsupervised approach to disentangle a scene into place, appearance, and occlusion features, where the place feature significantly increases the recall of place recognition under occlusion and changing appearance.

Ha-NeRF😆: Hallucinated Neural Radiance Fields in the Wild
Xingyu Chen, Qi Zhang†, Xiaoyu Li, Yue Chen, Ying Feng, Xuan Wang, Jue Wang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
project page / arXiv / paper / code / supplementary / video / poster

A framework to recover hallucinated neural radiance fields from tourism images with variable appearance and occlusions, consistently rendering free-occlusion views under different appearance hallucinations.


Projects
Deformation Field Estimation Using Fiber Bragg Grating Sensors
Yue Chen, Hu Sun
Xiamen University Outstanding Undergraduate Thesis Award, 2019

A study on deformation field estimation for the wing physical model using the Fiber Bragg Grating sensing network, which can be applied in aerospace structural health monitoring.


template adapted from this awesome website
Last updated: Mar 2023