Learning Non-Volumetric Depth Fusion Using Successive Reprojections

1 code implementation • CVPR 2019 • Simon Donne, Andreas Geiger

Given a set of input views, multi-view stereopsis techniques estimate depth maps to represent the 3D reconstruction of the scene; these are fused into a single, consistent, reconstruction -- most often a point cloud.

3D Reconstruction Depth Estimation

Point Triangulation Through Polyhedron Collapse Using the l[?] Norm

no code implementations • ICCV 2015 • Simon Donne, Bart Goossens, Wilfried Philips

Multi-camera triangulation of feature points based on a minimisation of the overall L2 reprojection error can get stuck in suboptimal local minima or require slow global optimisation.