Research
I'm interested in computer vision, deep learning, generative AI, and image processing.
I am recently working in the combination of 3D reconstruction and generation, especially in autonomous driving tasks.
Representative papers are highlighted .
MVGS:
Multi-View Regulated Gaussian Splatting for Novel View Synthesis
Xiaobiao Du ,
Yida Wang ,
Xin Yu
Arxiv , 2024
project page
/
arXiv /
Code
Star
MVGS is the first method to propose multi-view constraint learning for multi-view consistency.
Your browser does not support the video tag.
Mobile-GS: Real-time Gaussian Splatting for Mobile Devices
Xiaobiao Du ,
Yida Wang ,
Kun Zhan ,
Xin Yu
The Fourteenth International Conference on Learning Representations (ICLR) , 2026
project page
/
arXiv /
Code
Star
Mobile-GS is the first method to deploy 3DGS into mobile devices with real-time rendering speed.
Your browser does not support the video tag.
3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views
Xiaobiao Du ,
Yida Wang ,
Haiyang Sun ,
Zhuojie Wu ,
Hongwei Sheng ,
Shuyun Wang ,
Jiaying Ying ,
Ming Lu ,
Tianqing Zhu
Kun Zhan ,
Xin Yu
International Conference on Computer Vision (ICCV) , 2025
project page
/
arXiv /
Code
Star
3DRealCar is the first large-scale 360-degree 3D real car dataset.
Your browser does not support the video tag.
DreamCar: Leveraging Car-specific Prior for in-the-wild 3D Car Reconstruction
Xiaobiao Du ,
Haiyang Sun ,
Ming Lu ,
Tianqing Zhu
Xin Yu
IEEE Robotics and Automation Letters (RA-L) , 2024
project page
/
arXiv /
Code
Star
DreamCar helps you reconstruct a high-quality 3D car model, given only 1-5 images
Top Reviewer, NeurlPS 2025
Reviewer, ICLR, NIPS
Reviewer, ICCV, CVPR, ECCV
unique visitors since Apr 2024
This website takes the template from here .