Closed DWBSIC closed 1 year ago
Hi, they are gathered through the wireframe.py model, which should be called before the GlueStick model.
But the proper way to use GlueStick is to use the two_view_pipeline model, that combines both the wireframe and gluestick models. This is what is used in the demo notebook: https://github.com/cvg/GlueStick/blob/main/gluestick_matching_demo.ipynb
Thank you very much again for your research results. I look forward to your early open source of the new generation version of the code. Your research results will be very helpful to the community.
Thank you very much for your research results. Now I have a question, and I sincerely hope that you can answer it. I don't understand how to get these four parameters from data[]
lines0 = data['lines0'].flatten(1, 2) lines1 = data['lines1'].flatten(1, 2) lines_junc_idx0 = data['lines_junc_idx0'].flatten(1, 2) # [b_size, num_lines * 2] lines_junc_idx1 = data['lines_junc_idx1'].flatten(1, 2)