Explicitly define camera parameters rather than infer thru feature matching?

[claytonrothschild]

Hi,

If I know the transformation matrix of the camera for each photo, is there a way I can skip the feature matching step? Any insights appreciated.

  cameras = self.estimate_camera_parameters(features, matches)
  cameras = self.refine_camera_parameters(features, matches, cameras)
  cameras = self.perform_wave_correction(cameras)

Thank you.

[lukasalexanderweber]

It should work something like that, if I understand you correctly:

from stitching import Stitcher
from stitching.images import Images

class MyStitcher(Stitcher):

    def stitch_with_cameras(self, cameras, images, feature_masks=[]):
        self.images = Images.of(
            images, self.medium_megapix, self.low_megapix, self.final_megapix
        )
        
        # skip the registration part

        self.estimate_scale(cameras)
        imgs = self.resize_low_resolution()
        imgs, masks, corners, sizes = self.warp_low_resolution(imgs, cameras)
        self.prepare_cropper(imgs, masks, corners, sizes)
        imgs, masks, corners, sizes = self.crop_low_resolution(
            imgs, masks, corners, sizes
        )
        self.estimate_exposure_errors(corners, imgs, masks)
        seam_masks = self.find_seam_masks(imgs, corners, masks)

        imgs = self.resize_final_resolution()
        imgs, masks, corners, sizes = self.warp_final_resolution(imgs, cameras)
        imgs, masks, corners, sizes = self.crop_final_resolution(
            imgs, masks, corners, sizes
        )
        self.set_masks(masks)
        imgs = self.compensate_exposure_errors(corners, imgs)
        seam_masks = self.resize_seam_masks(seam_masks)

        self.initialize_composition(corners, sizes)
        self.blend_images(imgs, seam_masks, corners)
        return self.create_final_panorama()

and then

stitcher = MyStitcher()
panorama = stitcher.stitch(cameras, imgs)

[lukasalexanderweber]

@claytonrothschild did this work for your problem?