Abstract
The non-uniform blur of atmospheric turbulence can be modeled as a
superposition of linear motion blur kernels at a patch level. We
propose a regression convolutional neural network (CNN) to predict
angle and length of a linear motion blur kernel for varying sized
patches. We analyze the robustness of the network for different patch
sizes and the performance of the network in regions where the
characteristics of the blur are transitioning. Alternating patch sizes
per epoch in training, we find coefficient of determination scores
across a range of patch sizes of ${R^2} \gt 0.78$ for length and ${R^2} \gt 0.94$ for angle prediction. We find that
blur predictions in regions overlapping two blur characteristics
transition between the two characteristics as overlap changes. These
results validate the use of such a network for prediction of
non-uniform blur characteristics at a patch level.
© 2024 Optica Publishing Group
Full Article |
PDF Article
More Like This
Data availability
Data underlying the results presented in this paper for uniformly blurred images can be generated from the COCO dataset [25] via the code available at [27]. Data underlying the results for non-uniformly blurred images can be generated from the COCO dataset [25] via the code available at [29].
25. T.-Y. Lin, M. Maire, S. Belongie, et al., “Microsoft coco: common objects in context,” Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, 6 –12 September 2014 (Springer, 2014), pp. 740–755.
27. L. G. Varela and L. E. Boucheron, “Regression_blur,” GitHub, 2024, https://github.com/DuckDuckPig/Regression_Blur.
25. T.-Y. Lin, M. Maire, S. Belongie, et al., “Microsoft coco: common objects in context,” Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, 6 –12 September 2014 (Springer, 2014), pp. 740–755.
29. L. G. Varela and L. E. Boucheron, “Regression_ patch _
blur,” GitHub, 2024,
https://github.com/DuckDuckPig/RegressionPatchBlur.
Cited By
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription
Tables (2)
You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription
Equations (3)
You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription