Journal of Imaging, Volume 12, Issue 7
2026 July - 60 articles
Cover Story: Accurate correction of lens distortion is essential for applications such as 3D reconstruction, image registration, and camera calibration, particularly for specialised or disposable cameras, where only limited calibration data are available. We present a Deep Gaussian Process framework that models complex, spatially varying lens distortions, while also estimating the uncertainty of every corrected pixel. Unlike conventional methods that assume a single global distortion model, our approach adapts to local image behaviour and highlights regions where corrections are less reliable. Experiments on three challenging real-world camera systems demonstrate improved performance for highly irregular distortions, making the method well suited for next-generation scientific, medical, and industrial imaging devices. View this paper
- Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
- You may sign up for email alerts to receive table of contents of newly released issues.
- PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Articles
There are no articles in this issue yet.
J. Imaging - ISSN 2313-433X