Deep Learning-Based Image Stitching Technique Using Transformer 


Vol. 48,  No. 12, pp. 1577-1580, Dec.  2023
10.7840/kics.2023.48.12.1577


PDF
  Abstract

Image stitching is an image processing technique that combines multiple overlapping images into one. Classical image stitching extracts common feature keypoints from input images and use them as reference points for aligning the images. Convolutional neural network-based image stitching network combines latent feature vectors to produce stitched output from input overlapping images. This paper proposes a transformer-based image stitching network along with its implementation and training strategies. Unlike previous methods, the proposed transformerbased image stitching network explicitly learns to produce stitched output images from connection between patches of input images. It achieves 3.7dB higher PSNR and 0.12 higher SSIM than classical image stitching technique.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

B. Choi, S. Shin, J. Kim, S. An, J. Joo, H. Nam, "Deep Learning-Based Image Stitching Technique Using Transformer," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 12, pp. 1577-1580, 2023. DOI: 10.7840/kics.2023.48.12.1577.

[ACM Style]

Byungchan Choi, Seungwon Shin, Jihyun Kim, Sehwan An, Jihan Joo, and Haewoon Nam. 2023. Deep Learning-Based Image Stitching Technique Using Transformer. The Journal of Korean Institute of Communications and Information Sciences, 48, 12, (2023), 1577-1580. DOI: 10.7840/kics.2023.48.12.1577.

[KICS Style]

Byungchan Choi, Seungwon Shin, Jihyun Kim, Sehwan An, Jihan Joo, Haewoon Nam, "Deep Learning-Based Image Stitching Technique Using Transformer," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 12, pp. 1577-1580, 12. 2023. (https://doi.org/10.7840/kics.2023.48.12.1577)
Vol. 48, No. 12 Index