We lifted 14 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| ignacio-rocco/cnngeometric_pytorch | pwc_unofficial | 5 of 12 |
| Semanti1/cnngeometric_pytorch | reimplementation | 1 of 1 |
| yoyongbo/test | reimplementation | 0 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| correct_keypoints | Ran | Semanti1/cnngeometric_pytorch/eval_pf.py pointer only (licence: NONE) · get_code("cac8257f27511997") |
| default_collate | Ran | ignacio-rocco/cnngeometric_pytorch/util/dataloader.py code served (permissive licence) · get_code("eb5ca9515b0fe778") |
| featureL2Norm | Ran | ignacio-rocco/cnngeometric_pytorch/model/cnn_geometric_model.py code served (permissive licence) · get_code("cf9656ffec66503c") |
| normalize_axis | Ran | ignacio-rocco/cnngeometric_pytorch/geotnf/point_tnf.py code served (permissive licence) · get_code("2fa12cb30a255583") |
| str_to_bool | Ran | ignacio-rocco/cnngeometric_pytorch/util/torch_util.py code served (permissive licence) · get_code("8d87f08966a2f30c") |
| unnormalize_axis | Ran | ignacio-rocco/cnngeometric_pytorch/geotnf/point_tnf.py code served (permissive licence) · get_code("f78be05f4ea43f88") |
| PointsToUnitCoords | Not yet run | ignacio-rocco/cnngeometric_pytorch/geotnf/point_tnf.py code served (permissive licence) · get_code("17a7aebbcf3f2278") |
| correct_keypoints | Not yet run | yoyongbo/test/eval_pf.py pointer only (licence: NONE) · get_code("db9d075e05b7e7b3") |
| expand_dim | Not yet run | ignacio-rocco/cnngeometric_pytorch/util/torch_util.py code served (permissive licence) · get_code("82adf7750dd7a3e7") |
| homography_mat_from_4_pts | Not yet run | ignacio-rocco/cnngeometric_pytorch/geotnf/transformation.py code served (permissive licence) · get_code("d5dfacfde93f35b2") |
| normalize_image | Not yet run | ignacio-rocco/cnngeometric_pytorch/image/normalization.py code served (permissive licence) · get_code("6afbb61727662c3f") |
| pck | Not yet run | ignacio-rocco/cnngeometric_pytorch/util/eval_util.py code served (permissive licence) · get_code("389ddc75e927381b") |
| pin_memory_batch | Not yet run | ignacio-rocco/cnngeometric_pytorch/util/dataloader.py code served (permissive licence) · get_code("6d8c67dc116f1f8a") |
| read_flo_file | Not yet run | ignacio-rocco/cnngeometric_pytorch/geotnf/flow.py code served (permissive licence) · get_code("502159ccb250f467") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We address the problem of determining correspondences between two images in agreement with a geometric model such as an affine or thin-plate spline transformation, and estimating its parameters. The contributions of this work are three-fold. First, we propose a convolutional neural network architecture for geometric matching. The architecture is based on three main components that mimic the standard steps of feature extraction, matching and simultaneous inlier detection and model parameter estimation, while being trainable end-to-end. Second, we demonstrate that the network parameters can be trained from synthetically generated imagery without the need for manual annotation and that our matching layer significantly increases generalization capabilities to never seen before images. Finally, we show that the same model can perform both instance-level and category-level matching giving state-of-the-art results on the challenging Proposal Flow dataset.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1703.05593")
get_code_for_paper("1703.05593")
have("1703.05593")
Connect an agent — have() is free.