Reducing Drift in Structure From Motion Using Extended Features

TL;DR

This paper introduces a method that uses extended structural features like planes and vanishing points to significantly reduce drift in 3D structure from motion, especially in scenes with man-made structures, without relying on inertial data.

Contribution

The paper presents a novel approach that incorporates extended features as constraints in SfM to mitigate drift, enabling accurate reconstructions in challenging sequences.

Findings

Extended features span non-overlapping images, providing long-range constraints.

Significant drift reduction in scenes with long, man-made structures.

Effective in sequences without inertial measurements.

Abstract

Low-frequency long-range errors (drift) are an endemic problem in 3D structure from motion, and can often hamper reasonable reconstructions of the scene. In this paper, we present a method to dramatically reduce scale and positional drift by using extended structural features such as planes and vanishing points. Unlike traditional feature matches, our extended features are able to span non-overlapping input images, and hence provide long-range constraints on the scale and shape of the reconstruction. We add these features as additional constraints to a state-of-the-art global structure from motion algorithm and demonstrate that the added constraints enable the reconstruction of particularly drift-prone sequences such as long, low field-of-view videos without inertial measurements. Additionally, we provide an analysis of the drift-reducing capabilities of these constraints by evaluating on a synthetic dataset. Our structural features are able to significantly reduce drift for scenes that contain long-spanning man-made structures, such as aligned rows of windows or planar building facades.