João G. Atkinson A.

hey @isaaccorley, will you continue working on this?

as part of https://github.com/kornia/kornia/discussions/2719 plan, we have deleted the `master` in favor of `main`, if anyone has an interest in keep/restart working on this, let me know to help you.

link to https://github.com/kornia/kornia/issues/2064

as part of https://github.com/kornia/kornia/discussions/2719 plan, we have deleted the `master` in favor of `main`, if anyone has an interest in keep/restart working on this, let me know to help you.

> This should work as of the latest release: @charliermarsh do you have any plans to add support for the most common case? `uv pip install torch==2.1.0 --index-url https://download.pytorch.org/whl/cpu`

> Worth to double check that the internal imports are really absolutely pointing to the deepest submodule possible. We can trim after once we make sure and control over the...

this still relevant @edgarriba ?

> @johnnv1 our current Sam is not ONNX exportable, so I’d say yes it’s relevant but I won’t have time work on it Ok, just updated it to be main...

From #2226 > Not yet now, though. The seeming reason for failing to match same image, is because https://github.com/kornia/kornia/blob/master/kornia/feature/adalam/ransac.py#L58 AdaLAM RANSAC filters out "too perfect fits" and then some division...

is there a specific reason why we need separate APIs for 2D and 3D?