Panoramic Structure from Motion via Geometric Relationship Detection
It addresses a specific problem in computer vision for indoor panoramic reconstruction, offering a novel approach but appears incremental as it builds on existing SfM methods.
This paper tackles the problem of Structure from Motion for indoor panoramic image streams, which is challenging due to lack of textures and minimal parallax, by fusing single-view and multi-view reconstruction via geometric relationship detection, resulting in outperforming various state-of-the-art techniques on challenging datasets.
This paper addresses the problem of Structure from Motion (SfM) for indoor panoramic image streams, extremely challenging even for the state-of-the-art due to the lack of textures and minimal parallax. The key idea is the fusion of single-view and multi-view reconstruction techniques via geometric relationship detection (e.g., detecting 2D lines as coplanar in 3D). Rough geometry suffices to perform such detection, and our approach utilizes rough surface normal estimates from an image-to-normal deep network to discover geometric relationships among lines. The detected relationships provide exact geometric constraints in our line-based linear SfM formulation. A constrained linear least squares is used to reconstruct a 3D model and camera motions, followed by the bundle adjustment. We have validated our algorithm on challenging datasets, outperforming various state-of-the-art reconstruction techniques.