Presentation

<
MegaNorm: Local Patches Embedding for Efficient and Robust Point Normal Orientation at Super-Large Scale
SessionReconstruction
DescriptionMegaNorm is a fast, accurate, and robust method for orienting normals in non-watertight, scene-scale point clouds, scaling to ~50M points in under 10 minutes. It uses two feed-forward networks: one orients local patches in parallel, while a lightweight MLP evaluates pairwise consistency. Finally, a 0–1 integer program enforces global consistency.
Authors
Zhuodong Li
Institute of Software, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Zengke Liu
Institute of Software, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Fei Hou
Institute of Software, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Xuhui Chen
Institute of Software, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Wencheng Wang
Institute of Software, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Ying He
Nanyang Technological University
Event Type
Technical Paper
TimeWednesday, 22 July 202611:25am - 11:35am PDT
LocationRoom 408 B
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Wednesday, 22 July 202610:45am - 12:35pm PDTRoom 408 B
Keywords
Geometry
Modeling
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationResolution Where It Counts: Hash-based GPU-Accelerated 3D Reconstruction via Variance-Adaptive Voxel Grids
Similar Presentations
Surface Reconstruction from Unoriented Points via Green’s 3rd Identity
Points as Tori: Fast Pointwise Signed Distance for Point Clouds
Manifold k-NN: Accelerated k-NN Queries for Manifold Point Clouds