Mulin Yu
Scholar

Mulin Yu

Google Scholar ID: w0Od3hQAAAAJ
Shanghai AILab; INRIA
3D reconstruction and 3D repairing
Citations & Impact
All-time
Citations
815
 
H-index
7
 
i10-index
5
 
Publications
18
 
Co-authors
10
list available
Resume (English only)
Academic Achievements
  • Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes, CVPR, 2025
  • Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians, arXiv, 2024
  • GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction, Advances in Neural Information Processing Systems 37, 2024
  • Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering, CVPR, 2024
  • Sharp Feature Consolidation from Raw 3D Point Clouds via Displacement Learning, Computer Aided Geometric Design (CAGD), vol. 103, 2023
  • KIBS: 3D detection of planar roof sections from a single satellite image, ISPRS Journal of Photogrammetry and Remote Sensing 220, 2023
  • Repairing geometric errors in 3D urban models with kinetic data structures, ISPRS Journal of Photogrammetry and Remote Sensing (JPRS), Volume 192, 2022
  • Finding Good Configurations of Planar Primitives in Unorganized Point Clouds, CVPR, 2022
Research Experience
  • Current position: Researcher at Shanghai AI Lab; Formerly a Postdoctoral Researcher in the IDC research group at Shanghai AI Lab, working closely with Bo Dai and Dahua Lin.
Education
  • PhD from INRIA in 2022, supervised by Prof. Florent Lafarge.
Background
  • Research interests: 3D vision, scene reconstruction, surface reconstruction, city modeling, novel view synthesis, spatial point processes. Currently a Researcher at Shanghai AI Lab, exploring cutting-edge techniques in 3D vision and scene reconstruction.
Miscellany
  • Super Postdoc of Shanghai; Best Poster Award of MOMI 2022; Reviewer: CVPR, ECCV, TPAMI, CAD, JPRS, Siggraph...