CompoSE: Compositional Synthesis and Editing of 3D Shapes via Part-Aware Control
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913144529485824 |
|---|---|
| author | Slim, Habib Bhat, Shariq Farooq Elhoseiny, Mohamed Wang, Yifan Roberts, Mike |
| author_facet | Slim, Habib Bhat, Shariq Farooq Elhoseiny, Mohamed Wang, Yifan Roberts, Mike |
| contents | Creating and editing high-quality 3D content remains a central challenge in computer graphics. We address this challenge by introducing CompoSE, a novel method for Compositional Synthesis and Editing of 3D shapes via part-aware control. Our method takes as input a set of coarse geometric primitives (e.g., bounding boxes) that represent distinct object parts arranged in a particular spatial configuration, and synthesizes as output part-separated 3D objects that support localized granular (i.e., compositional) editing of individual parts. The key insight that enables our method is our use of a diffusion transformer architecture that alternates between processing each part locally and aggregating contextual information across parts globally, and features a novel conditioning technique that ensures strong adherence to the user's input. Importantly, our method learns to infer part semantics and symmetries directly from the user's coarse layout guidance, and does not require part-level text prompts. We demonstrate that our method enables powerful part-level editing capabilities, including context-aware substitution, addition, deletion, and style-preserving resizing operations. We show through extensive experiments that our method significantly outperforms existing approaches on guided synthesis, as measured by objective metrics and LLM-based evaluations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_19350 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CompoSE: Compositional Synthesis and Editing of 3D Shapes via Part-Aware Control Slim, Habib Bhat, Shariq Farooq Elhoseiny, Mohamed Wang, Yifan Roberts, Mike Graphics Machine Learning Creating and editing high-quality 3D content remains a central challenge in computer graphics. We address this challenge by introducing CompoSE, a novel method for Compositional Synthesis and Editing of 3D shapes via part-aware control. Our method takes as input a set of coarse geometric primitives (e.g., bounding boxes) that represent distinct object parts arranged in a particular spatial configuration, and synthesizes as output part-separated 3D objects that support localized granular (i.e., compositional) editing of individual parts. The key insight that enables our method is our use of a diffusion transformer architecture that alternates between processing each part locally and aggregating contextual information across parts globally, and features a novel conditioning technique that ensures strong adherence to the user's input. Importantly, our method learns to infer part semantics and symmetries directly from the user's coarse layout guidance, and does not require part-level text prompts. We demonstrate that our method enables powerful part-level editing capabilities, including context-aware substitution, addition, deletion, and style-preserving resizing operations. We show through extensive experiments that our method significantly outperforms existing approaches on guided synthesis, as measured by objective metrics and LLM-based evaluations. |
| title | CompoSE: Compositional Synthesis and Editing of 3D Shapes via Part-Aware Control |
| topic | Graphics Machine Learning |
| url | https://arxiv.org/abs/2605.19350 |