Robust SfM with Little Image Overlap

TL;DR

This paper introduces a novel SfM method capable of reconstructing scenes with minimal image overlap, using line coplanarity hypotheses and a robust RANSAC approach, enabling calibration in challenging scenarios.

Contribution

The method allows SfM with as few as two overlapping images by leveraging line coplanarity and relaxed trifocal constraints, expanding applicability to low-overlap datasets.

Findings

Successfully calibrates datasets with minimal overlap

Maintains accuracy despite relaxed constraints

Outperforms traditional SfM in low-overlap scenarios

Abstract

Usual Structure-from-Motion (SfM) techniques require at least trifocal overlaps to calibrate cameras and reconstruct a scene. We consider here scenarios of reduced image sets with little overlap, possibly as low as two images at most seeing the same part of the scene. We propose a new method, based on line coplanarity hypotheses, for estimating the relative scale of two independent bifocal calibrations sharing a camera, without the need of any trifocal information or Manhattan-world assumption. We use it to compute SfM in a chain of up-to-scale relative motions. For accuracy, we however also make use of trifocal information for line and/or point features, when present, relaxing usual trifocal constraints. For robustness to wrong assumptions and mismatches, we embed all constraints in a parameterless RANSAC-like approach. Experiments show that we can calibrate datasets that previously could not, and that this wider applicability does not come at the cost of inaccuracy.