Causal Reasoning Elicits Controllable 3D Scene Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914046845911040 |
|---|---|
| author | Chen, Shen Zhao, Ruiyu Zhou, Jiale Wu, Zongkai Hwang, Jenq-Neng Li, Lei |
| author_facet | Chen, Shen Zhao, Ruiyu Zhou, Jiale Wu, Zongkai Hwang, Jenq-Neng Li, Lei |
| contents | Existing 3D scene generation methods often struggle to model the complex logical dependencies and physical constraints between objects, limiting their ability to adapt to dynamic and realistic environments. We propose CausalStruct, a novel framework that embeds causal reasoning into 3D scene generation. Utilizing large language models (LLMs), We construct causal graphs where nodes represent objects and attributes, while edges encode causal dependencies and physical constraints. CausalStruct iteratively refines the scene layout by enforcing causal order to determine the placement order of objects and applies causal intervention to adjust the spatial configuration according to physics-driven constraints, ensuring consistency with textual descriptions and real-world dynamics. The refined scene causal graph informs subsequent optimization steps, employing a Proportional-Integral-Derivative(PID) controller to iteratively tune object scales and positions. Our method uses text or images to guide object placement and layout in 3D scenes, with 3D Gaussian Splatting and Score Distillation Sampling improving shape accuracy and rendering stability. Extensive experiments show that CausalStruct generates 3D scenes with enhanced logical coherence, realistic spatial interactions, and robust adaptability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15249 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Causal Reasoning Elicits Controllable 3D Scene Generation Chen, Shen Zhao, Ruiyu Zhou, Jiale Wu, Zongkai Hwang, Jenq-Neng Li, Lei Graphics Artificial Intelligence Existing 3D scene generation methods often struggle to model the complex logical dependencies and physical constraints between objects, limiting their ability to adapt to dynamic and realistic environments. We propose CausalStruct, a novel framework that embeds causal reasoning into 3D scene generation. Utilizing large language models (LLMs), We construct causal graphs where nodes represent objects and attributes, while edges encode causal dependencies and physical constraints. CausalStruct iteratively refines the scene layout by enforcing causal order to determine the placement order of objects and applies causal intervention to adjust the spatial configuration according to physics-driven constraints, ensuring consistency with textual descriptions and real-world dynamics. The refined scene causal graph informs subsequent optimization steps, employing a Proportional-Integral-Derivative(PID) controller to iteratively tune object scales and positions. Our method uses text or images to guide object placement and layout in 3D scenes, with 3D Gaussian Splatting and Score Distillation Sampling improving shape accuracy and rendering stability. Extensive experiments show that CausalStruct generates 3D scenes with enhanced logical coherence, realistic spatial interactions, and robust adaptability. |
| title | Causal Reasoning Elicits Controllable 3D Scene Generation |
| topic | Graphics Artificial Intelligence |
| url | https://arxiv.org/abs/2509.15249 |