Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2503.04919 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913723300446208 |
|---|---|
| author | Huang, Ian Bao, Yanan Truong, Karen Zhou, Howard Schmid, Cordelia Guibas, Leonidas Fathi, Alireza |
| author_facet | Huang, Ian Bao, Yanan Truong, Karen Zhou, Howard Schmid, Cordelia Guibas, Leonidas Fathi, Alireza |
| contents | Scene generation with 3D assets presents a complex challenge, requiring both high-level semantic understanding and low-level geometric reasoning. While Multimodal Large Language Models (MLLMs) excel at semantic tasks, their application to 3D scene generation is hindered by their limited grounding on 3D geometry. In this paper, we investigate how to best work with MLLMs in an object placement task. Towards this goal, we introduce a novel framework, FirePlace, that applies existing MLLMs in (1) 3D geometric reasoning and the extraction of relevant geometric details from the 3D scene, (2) constructing and solving geometric constraints on the extracted low-level geometry, and (3) pruning for final placements that conform to common sense. By combining geometric reasoning with real-world understanding of MLLMs, our method can propose object placements that satisfy both geometric constraints as well as high-level semantic common-sense considerations. Our experiments show that these capabilities allow our method to place objects more effectively in complex scenes with intricate geometry, surpassing the quality of prior work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04919 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement Huang, Ian Bao, Yanan Truong, Karen Zhou, Howard Schmid, Cordelia Guibas, Leonidas Fathi, Alireza Computer Vision and Pattern Recognition Scene generation with 3D assets presents a complex challenge, requiring both high-level semantic understanding and low-level geometric reasoning. While Multimodal Large Language Models (MLLMs) excel at semantic tasks, their application to 3D scene generation is hindered by their limited grounding on 3D geometry. In this paper, we investigate how to best work with MLLMs in an object placement task. Towards this goal, we introduce a novel framework, FirePlace, that applies existing MLLMs in (1) 3D geometric reasoning and the extraction of relevant geometric details from the 3D scene, (2) constructing and solving geometric constraints on the extracted low-level geometry, and (3) pruning for final placements that conform to common sense. By combining geometric reasoning with real-world understanding of MLLMs, our method can propose object placements that satisfy both geometric constraints as well as high-level semantic common-sense considerations. Our experiments show that these capabilities allow our method to place objects more effectively in complex scenes with intricate geometry, surpassing the quality of prior work. |
| title | FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.04919 |