Wei Hu, Renjie Liao, Xiang Gao, Bi'an Du
We lifted 8 functions out of this paper's own repositories and ran 3 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 |
|---|---|---|
| pkudba/3DHPA | canonical | 3 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| find_pts_ind | Ran | pkudba/3DHPA/prep_data/prepare_contact_points.py pointer only (licence: NONE) · get_code("64a95db50f18c0be") |
| get_pc_center | Ran | pkudba/3DHPA/prep_data/prepare_shape.py pointer only (licence: NONE) · get_code("44e0d54ee649fc5f") |
| get_pc_scale | Ran | pkudba/3DHPA/prep_data/prepare_shape.py pointer only (licence: NONE) · get_code("83ee4510bc9d2140") |
| build_ende | Not yet run | pkudba/3DHPA/exps/method/models/build_model.py pointer only (licence: NONE) · get_code("6441bb0f30ecee3e") |
| build_hpa | Not yet run | pkudba/3DHPA/exps/method/models/build_model.py pointer only (licence: NONE) · get_code("1365036de400539f") |
| cal_distance | Not yet run | pkudba/3DHPA/prep_data/prepare_contact_points.py pointer only (licence: NONE) · get_code("8a0324c5b838c5a5") |
| get_pair_list | Not yet run | pkudba/3DHPA/prep_data/prepare_contact_points.py pointer only (licence: NONE) · get_code("6c70807f90313071") |
| get_pca_axes | Not yet run | pkudba/3DHPA/prep_data/prepare_shape.py pointer only (licence: NONE) · get_code("1ee6aa8c251a9b6d") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Generative 3D part assembly involves understanding part relationships and predicting their 6-DoF poses for assembling a realistic 3D shape. Prior work often focus on the geometry of individual parts, neglecting part-whole hierarchies of objects. Leveraging two key observations: 1) super-part poses provide strong hints about part poses, and 2) predicting super-part poses is easier due to fewer superparts, we propose a part-whole-hierarchy message passing network for efficient 3D part assembly. We first introduce super-parts by grouping geometrically similar parts without any semantic labels. Then we employ a part-whole hierarchical encoder, wherein a super-part encoder predicts latent super-part poses based on input parts. Subsequently, we transform the point cloud using the latent poses, feeding it to the part encoder for aggregating super-part information and reasoning about part relationships to predict all part poses. In training, only ground-truth part poses are required. During inference, the predicted latent poses of super-parts enhance interpretability. Experimental results on the PartNet dataset show that our method achieves state-of-the-art performance in part and connectivity accuracy and enables an interpretable hierarchical part assembly. Code is available at https://github.com/pkudba/3DHPA.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.17464")
get_code_for_paper("2402.17464")
have("2402.17464")
Connect an agent — have() is free.