Fully automatic structure from motion with a spline-based environment representation
This addresses the challenge of accurately capturing structural regularities in man-made environments for computer vision applications, representing a novel method for a known bottleneck rather than an incremental improvement.
The paper tackles the problem of creating 3D environment representations from images by introducing a fully automatic pipeline that uses spline-based models (linked Bézier curves) instead of traditional sparse point clouds, achieving results that outperform state-of-the-art sparse feature-based methods and effectively model both straight and curved edges.
While the common environment representation in structure from motion is given by a sparse point cloud, the community has also investigated the use of lines to better enforce the inherent regularities in man-made surroundings. Following the potential of this idea, the present paper introduces a more flexible higher-order extension of points that provides a general model for structural edges in the environment, no matter if straight or curved. Our model relies on linked Bézier curves, the geometric intuition of which proves great benefits during parameter initialization and regularization. We present the first fully automatic pipeline that is able to generate spline-based representations without any human supervision. Besides a full graphical formulation of the problem, we introduce both geometric and photometric cues as well as higher-level concepts such overall curve visibility and viewing angle restrictions to automatically manage the correspondences in the graph. Results prove that curve-based structure from motion with splines is able to outperform state-of-the-art sparse feature-based methods, as well as to model curved edges in the environment.