Search Results for author:
Found 3 papers, 3 papers with code
Generalized Binary Search Network for Highly-Efficient Multi-View Stereo
The new formulation makes our method only sample a very small number of depth hypotheses in each step, which is highly memory efficient, and also greatly facilitates quick training convergence.
Ranked #7 on
3D Reconstruction
on DTU
DeepDT: Learning Geometry From Delaunay Triangulation for Surface Reconstruction
DeepDT learns to predict inside/outside labels of Delaunay tetrahedrons directly from a point cloud and corresponding Delaunay triangulation.
SSRNet: Scalable 3D Surface Reconstruction Network
Existing learning-based surface reconstruction methods from point clouds are still facing challenges in terms of scalability and preservation of details on large-scale point clouds.
