Turboreg is also good: Paper: http://bigwww.epfl.ch/publications/thevenaz9801.html Python implementation: https://pypi.org/project/pystackreg/
Would this work with images which are out of focus?
Accurate Image Alignment and Registration Using OpenCV
31–35 of 35 posts
Re: Accurate Image Alignment and Registration Using OpenCV
#32Earlier quoted context omitted.
Direct methods could be useful in your case. https://pages.cs.wisc.edu/~dyer/ai-qual/irani-visalg00.pdf
At work I had to make a custom image registration pipeline, that uses only 2 degrees of freedom, so just x,y translation. OpenCV did not have anything that did this, but a python library called Kornia does this well. https://kornia-tutorials.readthedocs.io/en/latest/image_regi...
Actually base-OpenCV has a great function for this: `cv2.findTransformECC()`:
https://learnopencv.com/image-alignment-ecc-in-opencv-c-pyth...
It can do dense translation, translation + rotation, Affine, and Homography alignment; I've used it in the past to do sub-pixel Aruco/AprilTag alignment (and I'd probably also use it for astrophotography).
Re: Accurate Image Alignment and Registration Using OpenCV
#33Earlier quoted context omitted.
Yes, I believe Google's team publicly says it helps add just enough random translation.
Do camera phones have mechanical shutters? I'm almost certain they don't.
On camera phones the random movements come from the users own instability when taking pictures.
Re: Accurate Image Alignment and Registration Using OpenCV
#34This is the kind of post I love to find in HN: an interesting topic and code. Does anyone know what is the theme of the blog? I am interested in how the references are created. I suppose it is based on something like RST.