Guiding Diffusion-Based Articulated Object Generation by Partial Point Cloud Alignment and Physical Plausibility Constraints
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916875200364544 |
|---|---|
| author | Kreber, Jens U. Stueckler, Joerg |
| author_facet | Kreber, Jens U. Stueckler, Joerg |
| contents | Articulated objects are an important type of interactable objects in everyday environments. In this paper, we propose PhysNAP, a novel diffusion model-based approach for generating articulated objects that aligns them with partial point clouds and improves their physical plausibility. The model represents part shapes by signed distance functions (SDFs). We guide the reverse diffusion process using a point cloud alignment loss computed using the predicted SDFs. Additionally, we impose non-penetration and mobility constraints based on the part SDFs for guiding the model to generate more physically plausible objects. We also make our diffusion approach category-aware to further improve point cloud alignment if category information is available. We evaluate the generative ability and constraint consistency of samples generated with PhysNAP using the PartNet-Mobility dataset. We also compare it with an unguided baseline diffusion model and demonstrate that PhysNAP can improve constraint consistency and provides a tradeoff with generative ability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00558 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Guiding Diffusion-Based Articulated Object Generation by Partial Point Cloud Alignment and Physical Plausibility Constraints Kreber, Jens U. Stueckler, Joerg Computer Vision and Pattern Recognition Machine Learning Articulated objects are an important type of interactable objects in everyday environments. In this paper, we propose PhysNAP, a novel diffusion model-based approach for generating articulated objects that aligns them with partial point clouds and improves their physical plausibility. The model represents part shapes by signed distance functions (SDFs). We guide the reverse diffusion process using a point cloud alignment loss computed using the predicted SDFs. Additionally, we impose non-penetration and mobility constraints based on the part SDFs for guiding the model to generate more physically plausible objects. We also make our diffusion approach category-aware to further improve point cloud alignment if category information is available. We evaluate the generative ability and constraint consistency of samples generated with PhysNAP using the PartNet-Mobility dataset. We also compare it with an unguided baseline diffusion model and demonstrate that PhysNAP can improve constraint consistency and provides a tradeoff with generative ability. |
| title | Guiding Diffusion-Based Articulated Object Generation by Partial Point Cloud Alignment and Physical Plausibility Constraints |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2508.00558 |