avatar

唐逍

TANG Xiao

spect@foxmail.com

Biography

I am currently a senior engineer in Huawei Noah's Ark Lab. Before that, I received the Ph.D. degree from The Chinese University of Hong Kong (CUHK), supervised by Prof. Chi-Wing Fu; and the B.Eng. degree from the University of Science and Technology of China (USTC).
Now I am still super passionate about computer graphics & 3D problems. 3D Reconstruction, Virtual Reality / Augmented Reality and Human-Computer Interaction fall within my research fields of interest.

Publications

OccluGaussian: Occlusion-Aware Gaussian Splatting for Large Scene Reconstruction and Rendering
Shiyong Liu*, Xiao Tang*, Zhihao Li*, Yingfan He, ChongJie Ye, Jianzhuang Liu, Binxiao Huang, Shunbo Zhou, Xiaofei Wu arxiv
We propose a scene-layout-aware division strategy for very large scenes, improving reconstruction quality and accelerating rendering.
SpecTRe-GS: Modeling Highly Specular Surfaces with Reflected Nearby Objects by Tracing Rays in 3D Gaussian Splatting
Jiajun Tang, Fan Fei, Zhihao Li, Xiao Tang, Shiyong Liu, Youyu Chen, Binxiao Huang, Zhenyu Chen, Xiaofei Wu, Boxin Shi The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025
We use 3D Gaussian ray tracing (3DGRT) to model surfaces with near-perfect reflections.
DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds
Youyu Chen, Junjun Jiang, Kui Jiang, Xiao Tang, Zhihao Li, Xianming Liu, Yinyu Nie The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025
We achieve an average speedup of 45.7% for most 3DGS backbones while preserving or even improving reconstruction quality.
Decoupling Appearance Variations with 3D Consistent Features in Gaussian Splatting
Jiaqi Lin, Zhihao Li, Binxiao Huang, Xiao Tang, Jianzhuang Liu, Shiyong Liu, Xiaofei Wu, Fenglong Song, Wenming Yang The Association for the Advancement of Artificial Intelligence (AAAI), 2025
We decouple appearance variations, even between day and night, enabling effective 3DGS reconstruction.
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 European Conference on Computer Vision (ECCV), 2024
We can reconstruction mirrors with prefect reflections in 3DGS.
VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction
Jiaqi Lin, Zhihao Li, Xiao Tang, Jianzhuang Liu, Shiyong Liu, Jiayue Liu, Yangdi Lu, Xiaofei Wu, Songcen Xu, Youliang Yan and Wenming Yang The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024
The first work to reconstruct very large scenes with 3DGS by scene division and appearance decoupling.
H2ONet: Hand-Occlusion-and-Orientation-aware Network for Real-time 3D Hand Mesh Reconstruction
Hao Xu, Tianyu Wang, Xiao Tang and Chi-Wing Fu The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023
We improve the hand mesh reconstuction under hand-object occlusion conditions.
CAFI-AR: Contact-aware Freehand Interaction with AR Objects
Xiao Tang, Ruihui Li and Chi-Wing Fu Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT, top jounal in Human-Computer Interaction), 2023
A system for real-hand virtual-object interaction in AR (implemented with Unity).
Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstruction
Xiao Tang, Tianyu Wang and Chi-Wing Fu International Conference on Computer Vision (ICCV), 2021
We enhance the reconstucted hand mesh to better align with captured images for AR interactions.
GrabAR: Occlusion-aware Grabbing Virtual Objects in AR
Xiao Tang, Xiaowei Hu, Chi-Wing Fu and Daniel Cohen-Or Proceedings of the ACM Symposium on User Interface Software and Technology (UIST, top conference in Human-Computer Interaction), 2020
We resolve the occlusion between real hands and virtual objects in real time for AR interactions.
Enhancing Augmented VR Interaction via Egocentric Scene Analysis
Yang Tian, Chi-Wing Fu, Shengdong Zhao, Ruihui Li, Xiao Tang, Xiaowei Hu, and Pheng-Ann Heng Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), 2019
We enhance user experience in interacting with physical objects with VR helmet on.
Computational Design of Wind-up Toys
Peng Song, Xiaofei Wang, Xiao Tang, Chi-Wing Fu, Hongfei Xu, Ligang Liu, and Niloy J. Mitra. ACM Transactions on Graphics (ACM TOG), vol. 36, no. 6, article no. 238, SIGGRAPH Asia, 2017.
A super interesting system to automatically design 3D-printed toys powered by clockwork motors.