Reducing Drift in Structure From Motion Using Extended Features
This addresses drift issues in 3D reconstruction for computer vision applications, particularly for scenes with man-made structures, but is an incremental improvement over existing global structure from motion methods.
The paper tackles the problem of drift in 3D structure from motion by using extended structural features like planes and vanishing points to provide long-range constraints, which significantly reduces scale and positional drift in drift-prone sequences such as long, low field-of-view videos.
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.