CTRL-C: Camera calibration TRansformer with Line-Classification

Cited 5 time in webofscience Cited 0 time in scopus
  • Hit : 102
  • Download : 0
Single image camera calibration is the task of estimating the camera parameters from a single input image, such as the vanishing points, focal length, and horizon line. In this work, we propose Camera calibration TRansformer with Line-Classification (CTRL-C), an end-to-end neural network-based approach to single image camera calibration, which directly estimates the camera parameters from an image and a set of line segments. Our network adopts the transformer architecture to capture the global structure of an image with multi-modal inputs in an end-to-end manner. We also propose an auxiliary task of line classification to train the network to extract the global geometric information from lines effectively. Our experiments demonstrate that CTRL-C outperforms the previous stateof-the-art methods on the Google Street View and SUN360 benchmark datasets. Code is available at https:// github. com/ jwlee-vcl/ CTRL-C.
Publisher
International Conference on Computer Vision
Issue Date
2021-10
Language
English
Citation

18th IEEE/CVF International Conference on Computer Vision (ICCV), pp.16208 - 16217

DOI
10.1109/ICCV48922.2021.01592
URI
http://hdl.handle.net/10203/289342
Appears in Collection
CS-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 5 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0