Multi-View Stereo 3D Edge Reconstruction

TL;DR

This paper introduces EdgeGraph3D, a novel system for reconstructing both straight and curved 3D edges from unordered image sequences, enhancing multi-view stereo surface accuracy especially under challenging lighting conditions.

Contribution

The work presents a new graph-based 2D edge representation and integrates it into a multi-view stereo pipeline, enabling 3D edge reconstruction beyond straight lines and points.

Findings

Effective in strong illumination changes and reflections

Improves surface reconstruction accuracy

Works with unordered image sequences

Abstract

This paper presents a novel method for the reconstruction of 3D edges in multi-view stereo scenarios. Previous research in the field typically relied on video sequences and limited the reconstruction process to either straight line-segments, or edge-points, i.e., 3D points that correspond to image edges. We instead propose a system, denoted as EdgeGraph3D, able to recover both straight and curved 3D edges from an unordered image sequence. A second contribution of this work is a graph-based representation for 2D edges that allows the identification of the most structurally significant edges detected in an image. We integrate EdgeGraph3D in a multi-view stereo reconstruction pipeline and analyze the benefits provided by 3D edges to the accuracy of the recovered surfaces. We evaluate the effectiveness of our approach on multiple datasets from two different collections in the multi-view stereo literature. Experimental results demonstrate the ability of EdgeGraph3D to work in presence of strong illumination changes and reflections, which are usually detrimental to the effectiveness of classical photometric reconstruction systems.