h12sawhney
h12sawhney
model-merger currently uses poses of two recons ONLY. I have witnessed large errors after aligning the two recons with model-merger. It will be nice to have an image re-projection based...
**Describe the bug** I copied a subset of the images, keypoints, descriptors, matches and two-view geometries from one DB in which I did feature extraction and exhaustive matching. I verified...
**Describe the bug** When I execute point_triangulator with zero BA iterations it does not produce any triangulation. I want to create an initial reconstruction of 3D points with pose specified....
I have tried running EVA01/EVA02 on Linux and Windows. All the tests go through. But the demo code is dysfuctional. You claim that you adopted the Detectron2 framework. In Detectron2...