We lifted 10 functions out of this paper's own repositories and ran 9 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 |
|---|---|---|
| pavlo-melnyk/tetrasphere | canonical | 9 of 10 |
| Function | Status | Where it lives |
|---|---|---|
| build_datasets | Ran | pavlo-melnyk/tetrasphere/tetrasphere/runner.py code served (permissive licence) · get_code("6550b40e98377f7d") |
| cal_loss | Ran | pavlo-melnyk/tetrasphere/tetrasphere/utils.py code served (permissive licence) · get_code("c6c2758c0c2fa756") |
| calculate_shape_IoU | Ran | pavlo-melnyk/tetrasphere/tetrasphere/utils.py code served (permissive licence) · get_code("ed28493d8df0a024") |
| embed | Ran | pavlo-melnyk/tetrasphere/tetrasphere/models/spheres.py code served (permissive licence) · get_code("e4b543f085e11201") |
| embed_spheres | Ran | pavlo-melnyk/tetrasphere/tetrasphere/models/spheres.py code served (permissive licence) · get_code("c8619d0a79c0c42d") |
| get_graph_feature | Ran | pavlo-melnyk/tetrasphere/tetrasphere/models/utils.py code served (permissive licence) · get_code("e146f86f54b1a708") |
| knn | Ran | pavlo-melnyk/tetrasphere/tetrasphere/models/utils.py code served (permissive licence) · get_code("cdd0141594039dcb") |
| mean_pool | Ran | pavlo-melnyk/tetrasphere/tetrasphere/models/vnn.py code served (permissive licence) · get_code("19b639ea820e6dbc") |
| nd_get_graph_feature | Ran | pavlo-melnyk/tetrasphere/tetrasphere/models/utils.py code served (permissive licence) · get_code("111defecda8c385d") |
| append_ones | Not yet run | pavlo-melnyk/tetrasphere/tetrasphere/models/spheres.py code served (permissive licence) · get_code("3a71074992fa1e26") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In many practical applications, 3D point cloud analysis requires rotation invariance. In this paper, we present a learnable descriptor invariant under 3D rotations and reflections, i.e., the O(3) actions, utilizing the recently introduced steerable 3D spherical neurons and vector neurons. Specifically, we propose an embedding of the 3D spherical neurons into 4D vector neurons, which leverages end-to-end training of the model. In our approach, we perform TetraTransform--an equivariant embedding of the 3D input into 4D, constructed from the steerable neurons--and extract deeper O(3)-equivariant features using vector neurons. This integration of the TetraTransform into the VN-DGCNN framework, termed TetraSphere, negligibly increases the number of parameters by less than 0.0002%. TetraSphere sets a new state-of-the-art performance classifying randomly rotated real-world object scans of the challenging subsets of ScanObjectNN. Additionally, TetraSphere outperforms all equivariant methods on randomly rotated synthetic data: classifying objects from ModelNet40 and segmenting parts of the ShapeNet shapes. Thus, our results reveal the practical value of steerable 3D spherical neurons for learning in 3D Euclidean space. The code is available at https://github.com/pavlo-melnyk/tetrasphere.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2211.14456")
get_code_for_paper("2211.14456")
have("2211.14456")
Connect an agent — have() is free.