Taskonomy: Disentangling task transfer learning
Do visual tasks have a relationship, or are they unrelated? For instance, could having
surface normals simplify estimating the depth of an image? Intuition answers these …
surface normals simplify estimating the depth of an image? Intuition answers these …
Gluestick: Robust image matching by sticking points and lines together
Line segments are powerful features complementary to points. They offer structural cues,
robust to drastic viewpoint and illumination changes, and can be present even in texture …
robust to drastic viewpoint and illumination changes, and can be present even in texture …
An efficient and robust line segment matching approach based on LBD descriptor and pairwise geometric consistency
L Zhang, R Koch - Journal of visual communication and image …, 2013 - Elsevier
We present a line matching algorithm which utilizes both the local appearance of lines and
their geometric attributes. To overcome the problem of segment fragmentation and …
their geometric attributes. To overcome the problem of segment fragmentation and …
SOLD2: Self-supervised occlusion-aware line description and detection
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 …
offer additional challenges. Yet, line features represent a promising complement to points for …
A comprehensive review of image line segment detection and description: Taxonomies, comparisons, and challenges
An image line segment is a fundamental low-level visual feature that delineates straight,
slender, and uninterrupted portionsof objects and scenarios within images. Detection and …
slender, and uninterrupted portionsof objects and scenarios within images. Detection and …
Line as a visual sentence: Context-aware line descriptor for visual localization
Along with feature points for image matching, line features provide additional constraints to
solve visual geometric problems in robotics and computer vision (CV). Although recent …
solve visual geometric problems in robotics and computer vision (CV). Although recent …
A framework for augmented reality guidance in industry
Nowadays, many companies see augmented reality (AR) as an important tool to provide
new services related to their products. However, many challenges remain to be solved for …
new services related to their products. However, many challenges remain to be solved for …
Robust line matching through line–point invariants
B Fan, F Wu, Z Hu - Pattern Recognition, 2012 - Elsevier
This paper is about line matching by line–point invariants which encode local geometric
information between a line and its neighboring points. Specifically, two kinds of line–point …
information between a line and its neighboring points. Specifically, two kinds of line–point …
Hierarchical line matching based on line–junction–line structure descriptor and local homography estimation
This paper presents a hierarchical method for matching line segments from two images. Line
segments are matched first in groups and then in individuals. While matched in groups, the …
segments are matched first in groups and then in individuals. While matched in groups, the …
Robust line segment mismatch removal using point-pair representation and Gaussian-uniform mixture formulation
Line segment matching (LSM) plays an important role in image matching, while it is always a
challenging problem due to line fracture and high geometric complexity. In this paper, we …
challenging problem due to line fracture and high geometric complexity. In this paper, we …