Improve 3D surface reconstruction from point clouds using geometry in distance function with GeoUDF
Improve 3D surface reconstruction from point clouds using geometry in distance function with GeoUDF
GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation
arXiv paper abstract https://arxiv.org/abs/2211.16762
arXiv PDF paper https://arxiv.org/pdf/2211.16762.pdf
GitHub https://github.com/rsy6318/geoudf
The recent neural implicit representation-based methods have greatly advanced … solving the long-standing and challenging problem of reconstructing a discrete surface from a sparse point cloud.
These methods generally learn either a binary occupancy or signed/unsigned distance field (SDF/UDF) as surface representation.
However, all the existing SDF/UDF-based methods use neural networks to implicitly regress the distance in a purely data-driven manner, thus limiting the accuracy and generalizability
… propose the first geometry-guided method for UDF and its gradient estimation that explicitly formulates the unsigned distance of a query point as the learnable affine averaging of its distances to the tangent planes of neighbouring points.
… model the local geometric structure of the input point clouds by explicitly learning a quadratic polynomial for each point.
… demonstrate the significant advantages of … method over state-of-the-art methods in terms of reconstruction accuracy, efficiency, and generalizability …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
