RoMaFeatureMatcherOptions

giant.image_processing.feature_matchers:

class giant.image_processing.feature_matchers.RoMaFeatureMatcherOptions(device: torch.device = <factory>, coarse_res: int | tuple[int, int] = 560, upsample_res: tuple[int, int] = (864, 864), sample_thresh: float = 0.05)[source]
Parameters:

  • device (device)

  • coarse_res (int | tuple[int, int])

  • upsample_res (tuple[int, int])

  • sample_thresh (float)

device: device

What device to work on

coarse_res: int | tuple[int, int] = 560

The initial coarse resolution of the image (must be a multiple of 14)

upsample_res: tuple[int, int] = (864, 864)

The resolution to upsample the image to

sample_thresh: float = 0.05

Controls the thresholding used when sampling matches for estimation.

In certain cases a lower or higher threshold may improve results.

property options_dict: Dict

Determine the options input to the dataclass.

This property method will ignore all internal properties and functions

Summary of Methods

apply_options

Update the options as attributes of the object class

local_vars

this is used to overwrite options in variables only used in __init__

override_options

This method is used for special cases when certain options should be overwritten