Facetwise Mesh Refinement for Multi-View Stereo

TL;DR

This paper introduces a facetwise mesh refinement method for multi-view stereo that preemptively repairs non-manifold vertices and optimally selects camera pairs for each mesh facet, improving refinement accuracy and evenness.

Contribution

It extends volumetric mesh refinement by directly fixing non-manifold vertices during Delaunay Triangulation and introduces a novel camera pair selection strategy per facet.

Findings

Reduces non-manifold vertices without explicit vertex splits.

Enhances refinement accuracy by selecting optimal camera pairs per facet.

Achieves more even and effective mesh refinement.

Abstract

Mesh refinement is a fundamental step for accurate Multi-View Stereo. It modifies the geometry of an initial manifold mesh to minimize the photometric error induced in a set of camera pairs. This initial mesh is usually the output of volumetric 3D reconstruction based on min-cut over Delaunay Triangulations. Such methods produce a significant amount of non-manifold vertices, therefore they require a vertex split step to explicitly repair them. In this paper, we extend this method to preemptively fix the non-manifold vertices by reasoning directly on the Delaunay Triangulation and avoid most vertex splits. The main contribution of this paper addresses the problem of choosing the camera pairs adopted by the refinement process. We treat the problem as a mesh labeling process, where each label corresponds to a camera pair. Differently from the state-of-the-art methods, which use each camera pair to refine all the visible parts of the mesh, we choose, for each facet, the best pair that enforces both the overall visibility and coverage. The refinement step is applied for each facet using only the camera pair selected. This facetwise refinement helps the process to be applied in the most evenly way possible.