CVMar 23, 2017

Robust SfM with Little Image Overlap

arXiv:1703.07957v2
Originality Incremental advance
AI Analysis

This addresses a bottleneck in 3D reconstruction for applications with sparse image sets, representing an incremental improvement over traditional SfM techniques.

The paper tackles the problem of Structure-from-Motion (SfM) in scenarios with minimal image overlap, such as only two images per scene part, by proposing a method based on line coplanarity hypotheses to estimate relative scales without trifocal information. Experiments show it successfully calibrates previously unmanageable datasets without sacrificing accuracy.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes