GAOT: Generating Articulated Objects Through Text-Guided Diffusion Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912745995108352 |
|---|---|
| author | Sun, Hao Fan, Lei Di, Donglin Liu, Shaohui |
| author_facet | Sun, Hao Fan, Lei Di, Donglin Liu, Shaohui |
| contents | Articulated object generation has seen increasing advancements, yet existing models often lack the ability to be conditioned on text prompts. To address the significant gap between textual descriptions and 3D articulated object representations, we propose GAOT, a three-phase framework that generates articulated objects from text prompts, leveraging diffusion models and hypergraph learning in a three-step process. First, we fine-tune a point cloud generation model to produce a coarse representation of objects from text prompts. Given the inherent connection between articulated objects and graph structures, we design a hypergraph-based learning method to refine these coarse representations, representing object parts as graph vertices. Finally, leveraging a diffusion model, the joints of articulated objects-represented as graph edges-are generated based on the object parts. Extensive qualitative and quantitative experiments on the PartNet-Mobility dataset demonstrate the effectiveness of our approach, achieving superior performance over previous methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_03566 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GAOT: Generating Articulated Objects Through Text-Guided Diffusion Models Sun, Hao Fan, Lei Di, Donglin Liu, Shaohui Computer Vision and Pattern Recognition Multimedia Articulated object generation has seen increasing advancements, yet existing models often lack the ability to be conditioned on text prompts. To address the significant gap between textual descriptions and 3D articulated object representations, we propose GAOT, a three-phase framework that generates articulated objects from text prompts, leveraging diffusion models and hypergraph learning in a three-step process. First, we fine-tune a point cloud generation model to produce a coarse representation of objects from text prompts. Given the inherent connection between articulated objects and graph structures, we design a hypergraph-based learning method to refine these coarse representations, representing object parts as graph vertices. Finally, leveraging a diffusion model, the joints of articulated objects-represented as graph edges-are generated based on the object parts. Extensive qualitative and quantitative experiments on the PartNet-Mobility dataset demonstrate the effectiveness of our approach, achieving superior performance over previous methods. |
| title | GAOT: Generating Articulated Objects Through Text-Guided Diffusion Models |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2512.03566 |