Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

SOLD2 : Self-supervised occlusion-aware line description and detection

Pautrat, Rémi ; Lin, Juan-Ting ; Larsson, Viktor LU ; Oswald, Martin R and Pollefeys, Marc (2021) 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 p.11363-11373
Abstract
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... (More)
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. (Less)
Please use this url to cite or link to this publication:
author
; ; ; and
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
pages
11 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
conference location
Virtual, Online, United States
conference dates
2021-06-19 - 2021-06-25
DOI
10.1109/CVPR46437.2021.01121
language
English
LU publication?
no
id
0eb2dd71-a23b-4e00-9898-0a9f9960a8e4
date added to LUP
2022-09-06 13:20:21
date last changed
2022-09-20 19:04:01
@inproceedings{0eb2dd71-a23b-4e00-9898-0a9f9960a8e4,
  abstract     = {{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.}},
  author       = {{Pautrat, Rémi and Lin, Juan-Ting and Larsson, Viktor and Oswald, Martin R and Pollefeys, Marc}},
  booktitle    = {{2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}},
  language     = {{eng}},
  pages        = {{11363--11373}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{SOLD2 : Self-supervised occlusion-aware line description and detection}},
  url          = {{http://dx.doi.org/10.1109/CVPR46437.2021.01121}},
  doi          = {{10.1109/CVPR46437.2021.01121}},
  year         = {{2021}},
}