|
Shiyong Liu I'm a research scientist at Huawei Noah's Ark Lab in ShenZhen, China, where I work on a small team that mostly works on 3DGS. At Huawei I've worked on Large Scene Reconstruction, Camera Poses Estimation, Motion Capture, VR, Multi-model Recommendation & Search, Defect Detection and Machine Vision. I did my Master degree at National University of Defense Technology (NUDT). |
|
ResearchI'm interested in 3D computer vision, including camera pose estimation, motion capture and 3D reconstrucrion. Some papers are highlighted. |
|
Vastgaussian: Vast 3d gaussians for large scene reconstruction
Jiaqi Ling, Zhihao Li, Jianzhuang Liu, Shiyong Liu, Yangdi Lu, Xiaofei Wu Songcen Xu Youliang Yan Wenming Yang CVPR, 2024 project page / arXiv An approach for large scene reconstruction that enabling fast optimization and high-fidelity real-time rendering. |
|
Mirrorgaussian: Reflecting 3d gaussians for reconstructing mirror reflections
Jiayue Liu, Xiao Tang, Freeman Cheng, Roy Yang, Zhihao Li, Jianzhuang Liu, Yi Huang, Jiaqi Lin, Shiyong Liu, Xiaofei Wu Songcen Xu Chun Yuan ECCV, 2024 project page / arXiv MirrorGaussian achieves high-quality and real-time rendering in scenes with mirrors, empowering scene editing like adding new mirrors and objects. |
Miscellanea |
|
Thanks for Jon Barron's website open source source code. |