Original images:
Straightened images(user specified lines in purple):
As you could probably tell either I didn't pick the right pictures or I had not idea which parts to straighten, so this method works best if the user knows what he is doing.
Friday, June 18, 2010
Wide-angle image straightening
This is by far the trickiest energy-based optimization I have ever implemented. The idea is quite similar to the spectral conformal parameterization algorithm I have used for the model viewer, however, it requires more energy terms and hence more tune-ups to work properly. The main purpose of the paper is to let the user identify straight lines that are bent by the wide-angle photography, especially fish-eye lens, to preserve certain content. It makes some good use of stereographic projection to help converge to the final result, and especially the smoothing terms that prevent distortion. Let's look at a few examples:
As you could probably tell either I didn't pick the right pictures or I had not idea which parts to straighten, so this method works best if the user knows what he is doing.
As you could probably tell either I didn't pick the right pictures or I had not idea which parts to straighten, so this method works best if the user knows what he is doing.
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment