Mårten Björkman

Repeatability test

1

After seeing the paper ["PopSift: a faithful SIFT implementation for real-time applications"](https://github.com/alicevision/popsift) in which the authors claim CudaSift to perform exceptionally poor with respect to scale changes, I got a...

Suggestions for future versions?

6

After the latests commits I'm running out of ideas of what to improve and would like to hear if anyone has any suggestions for future versions. For further speed improvements,...

Question about discretization

4

How is the discretization due to subsampling accounted for in the nlp steps? For each increasing octave derivates are approximated with increasing step lengths in terms of the original image,...