Complement (music)

Phenotype

Pattern recognition (psychology)

Feature (linguistics)

Mathematics

Interest point detection

Pipeline (software)

Discriminative model

Gene

Image (mathematics)

Statistics

Feature detection (computer vision)

Philosophy

Artificial intelligence

Matching (statistics)

Set (abstract data type)

Chemistry

Parsing

Complementation

Line (geometry)

Programming language

Geometry

Code (set theory)

Computer science

Linguistics

Feature extraction

Point (geometry)

Computer vision

Biochemistry

Telecommunications

Image processing

Detector

Compared to feature point detection and description, detecting and matching line segments offer additional challenges. Yet, line features represent a promising complement to points for multi-view tasks. Lines are indeed well-defined by the image gradient, frequently appear even in poorly textured areas and offer robust structural cues. We thus hereby introduce the first joint detection and description of line segments in a single deep network. Thanks to a self-supervised training, our method does not require any annotated line labels and can therefore generalize to any dataset. Our detector offers repeatable and accurate localization of line segments in images, departing from the wireframe parsing approach. Leveraging the recent progresses in descriptor learning, our proposed line descriptor is highly discriminative, while remaining robust to viewpoint changes and occlusions. We evaluate our approach against previous line detection and description methods on several multi-view datasets created with homographic warps as well as real-world viewpoint changes. Our full pipeline yields higher repeatability, localization accuracy and matching metrics, and thus represents a first step to bridge the gap with learned feature points methods. Code and trained weights are available at https://github.com/cvg/SOLD2.

SOLD<sup>2</sup>: Self-supervised Occlusion-aware Line Description and Detection

SOLD2: Self-supervised Occlusion-aware Line Description and Detection

SOLD²: Self-supervised Occlusion-aware Line Description and Detection