import matplotlib.pyplot as plt import cv2 import kornia as K import kornia.feature as KF import numpy as np import torch from kornia_moons.feature import * import gradio as gr def load_torch_image(fname): img: Tensor = K.io.load_image(fname, K.io.ImageLoadType.RGB32) img = img[None] # 1xCxHxW / fp32 / [0, 1] img = K.geometry.resize(img, (700, 700)) return img def inference(file1,file2): fname1 = file1.name fname2 = file2.name img1 = load_torch_image(im1re) img2 = load_torch_image(im2re) matcher = KF.LoFTR(pretrained='outdoor') input_dict = {"image0": K.color.rgb_to_grayscale(img1), # LofTR works on grayscale images only "image1": K.color.rgb_to_grayscale(img2)} with torch.no_grad(): correspondences = matcher(input_dict) mkpts0 = correspondences['keypoints0'].cpu().numpy() mkpts1 = correspondences['keypoints1'].cpu().numpy() H, inliers = cv2.findFundamentalMat(mkpts0, mkpts1, cv2.USAC_MAGSAC, 0.5, 0.999, 100000) inliers = inliers > 0 fig, ax = plt.subplots() draw_LAF_matches( KF.laf_from_center_scale_ori(torch.from_numpy(mkpts0).view(1,-1, 2), torch.ones(mkpts0.shape[0]).view(1,-1, 1, 1), torch.ones(mkpts0.shape[0]).view(1,-1, 1)), KF.laf_from_center_scale_ori(torch.from_numpy(mkpts1).view(1,-1, 2), torch.ones(mkpts1.shape[0]).view(1,-1, 1, 1), torch.ones(mkpts1.shape[0]).view(1,-1, 1)), torch.arange(mkpts0.shape[0]).view(-1,1).repeat(1,2), K.tensor_to_image(img1), K.tensor_to_image(img2), inliers, draw_dict={'inlier_color': (0.2, 1, 0.2), 'tentative_color': None, 'feature_color': (0.2, 0.5, 1), 'vertical': False}, ax=ax) plt.axis('off') fig.savefig('example.jpg',dpi=110,bbox_inches='tight') return 'example.jpg' title = "Kornia-Loftr" description = "Gradio demo for Kornia-Loftr: Detector-Free Local Feature Matching with Transformers. To use it, simply upload your image, or click one of the examples to load them. Read more at the links below." article = "

Open Source Differentiable Computer Vision Library | Kornia Github Repo | LoFTR Github | LoFTR: Detector-Free Local Feature Matching with Transformers

" css = ".output_image, .input_image {height: 40rem !important; width: 100% !important;}" examples = [['kn_church-2.jpg','kn_church-8.jpg']] gr.Interface( inference, [gr.inputs.Image(type="file", label="Input1"),gr.inputs.Image(type="file", label="Input2")], gr.outputs.Image(type="file", label="Output"), title=title, description=description, article=article, enable_queue=True, examples=examples, css=css ).launch(debug=True)