pycpd
pycpd copied to clipboard
siavashk
Pure Numpy Implementation of the Coherent Point Drift Algorithm
In my pycpd fork, I've implemented the cpd extension described in https://ieeexplore.ieee.org/document/7477719 It allows users to add correspondence priors with varying degrees of confidence (from reliable to unreliable) to the...
Can be done with scale flag during initialization of RigidRegistration class. Set to True by default.
Thanks for the code. Now I have two sets of points, one is a template, and the other is the same as the template but has some noisy points and...
Hello everyone, I am currently working on my master thesis and would like to use this library for it. To be able to tackle my actual task, I first need...
Hi, the parameter w is not checked for range, so this line: c = c * self.w / (1 - self.w) can divide by zero. How about an additional line...
Using 1. np.sum(P, axis = 0, keepdims = True) instead of tile 2. clip instead of indexing and assignment
Hello, I am using pycpd in my work and want to acknowledge pycpd package by citing it. Apart from the original CPD paper by Myronenko and Song, is there any...
Hi! First off: Thanks for this great library! I'm working with data where I frequently also need to apply the inverse transform, i.e `target->source` instead of `source->target`. I was wondering...
Hi @gattia and @siavashk, This is part of the JOSS review process. I found two minor issues after testing your PyCPD package. Could you please address them? - Found an...
Part of reviewing process for JOSS acceptance (openjournals/joss-reviews/issues/4681) I couldn't find clear instructions on how to participate in this project. Ideally you should provide a CONTRIBUTE file with some informations...
