ScaleLSD: Scalable Deep Line Segment Detection Streamlined
This work provides a robust, domain-agnostic solution for line geometry characterization in natural images, significantly enhancing versatility for applications in computer vision, though it is incremental as it builds upon existing LSD methods.
The paper tackles the problem of Line Segment Detection (LSD) in images by developing ScaleLSD, a scalable self-supervised deep learning model that outperforms the pioneering non-deep LSD approach, detecting more line segments with better accuracy and completeness across various tasks like 3D geometry estimation and line matching.
This paper studies the problem of Line Segment Detection (LSD) for the characterization of line geometry in images, with the aim of learning a domain-agnostic robust LSD model that works well for any natural images. With the focus of scalable self-supervised learning of LSD, we revisit and streamline the fundamental designs of (deep and non-deep) LSD approaches to have a high-performing and efficient LSD learner, dubbed as ScaleLSD, for the curation of line geometry at scale from over 10M unlabeled real-world images. Our ScaleLSD works very well to detect much more number of line segments from any natural images even than the pioneered non-deep LSD approach, having a more complete and accurate geometric characterization of images using line segments. Experimentally, our proposed ScaleLSD is comprehensively testified under zero-shot protocols in detection performance, single-view 3D geometry estimation, two-view line segment matching, and multiview 3D line mapping, all with excellent performance obtained. Based on the thorough evaluation, our ScaleLSD is observed to be the first deep approach that outperforms the pioneered non-deep LSD in all aspects we have tested, significantly expanding and reinforcing the versatility of the line geometry of images. Code and Models are available at https://github.com/ant-research/scalelsd