Mulin Yu 于沐霖

 

I am currently a Researcher at Shanghai AI Lab, where I explore cutting-edge techniques in 3D vision and scene reconstruction. Before that, I was a Postdoctoral Researcher in the IDC research group at Shanghai AI Lab, working closely with Bo Dai and Dahua Lin. I earned my PhD from INRIA in 2022, under the supervision of Prof. Florent Lafarge. My research passion lies in surface reconstruction, city modeling, novel view synthesis, and spatial point processes—bringing digital worlds to life with precision and realism.



Publications

Google Scholar Profile

   

Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes
Lihan Jiang*, Kerui Ren*, Mulin Yu, Linning Xu, Junting Dong, Tao Lu, Feng Zhao, Dahua Lin and Bo Dai
CVPR, 2025
Project page     paper

   

Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians
Kerui Ren*, Lihan Jiang*, Tao Lu, Mulin Yu, Linning Xu and Bo Dai
arXiv, 2024
Project page     paper     code

   

GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction
Mulin Yu*, Tao Lu*, Linning Xu, Lihan Jiang, Yuanbo Xiangli, and Bo Dai
Advances in Neural Information Processing Systems 37, 129507-129530
Project page     paper     code

   

Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering
Tao Lu*, Mulin Yu*, Linning Xu, Yuanbo Xiangli, Limin Wang, Dahua Lin and Bo Dai
CVPR, 2024, highlight
Project page     paper     code

   

Sharp Feature Consolidation from Raw 3D Point Clouds via Displacement Learning
Tong Zhao*, Mulin Yu*, Pierre Alliez, and Florent Lafarge
Computer Aided Geometric Design (CAGD), vol. 103 (2023)
paper     code

   

KIBS: 3D detection of planar roof sections from a single satellite image
Johann Lussange, Mulin Yu, Yuliya Tarabalka, Florent Lafarge
ISPRS Journal of Photogrammetry and Remote Sensing 220, 207-216
paper    

   

Repairing geometric errors in 3D urban models with kinetic data structures
Mulin Yu, Florent Lafarge, Sven Oesau, and Bruno Hilaire
ISPRS Journal of Photogrammetry and Remote Sensing (JPRS), Volume 192, 2022
paper

   

Finding Good Configurations of Planar Primitives in Unorganized Point Clouds
Mulin Yu, and Florent Lafarge
Computer Vision and Pattern Recognition (CVPR), 2022
paper     supplementary     code


Activities