RoomPlanner: Explicit Layout Planner for Easier LLM-Driven 3D Room Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908668888350720 |
|---|---|
| author | Sun, Wenzhuo Liang, Mingjian Song, Wenxuan Cheng, Xuelian Ge, Zongyuan |
| author_facet | Sun, Wenzhuo Liang, Mingjian Song, Wenxuan Cheng, Xuelian Ge, Zongyuan |
| contents | In this paper, we propose RoomPlanner, the first fully automatic 3D room generation framework for painlessly creating realistic indoor scenes with only short text as input. Without any manual layout design or panoramic image guidance, our framework can generate explicit layout criteria for rational spatial placement. We begin by introducing a hierarchical structure of language-driven agent planners that can automatically parse short and ambiguous prompts into detailed scene descriptions. These descriptions include raw spatial and semantic attributes for each object and the background, which are then used to initialize 3D point clouds. To position objects within bounded environments, we implement two arrangement constraints that iteratively optimize spatial arrangements, ensuring a collision-free and accessible layout solution. In the final rendering stage, we propose a novel AnyReach Sampling strategy for camera trajectory, along with the Interval Timestep Flow Sampling (ITFS) strategy, to efficiently optimize the coarse 3D Gaussian scene representation. These approaches help reduce the total generation time to under 30 minutes. Extensive experiments demonstrate that our method can produce geometrically rational 3D indoor scenes, surpassing prior approaches in both rendering speed and visual quality while preserving editability. The code will be available soon. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_17048 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RoomPlanner: Explicit Layout Planner for Easier LLM-Driven 3D Room Generation Sun, Wenzhuo Liang, Mingjian Song, Wenxuan Cheng, Xuelian Ge, Zongyuan Computer Vision and Pattern Recognition In this paper, we propose RoomPlanner, the first fully automatic 3D room generation framework for painlessly creating realistic indoor scenes with only short text as input. Without any manual layout design or panoramic image guidance, our framework can generate explicit layout criteria for rational spatial placement. We begin by introducing a hierarchical structure of language-driven agent planners that can automatically parse short and ambiguous prompts into detailed scene descriptions. These descriptions include raw spatial and semantic attributes for each object and the background, which are then used to initialize 3D point clouds. To position objects within bounded environments, we implement two arrangement constraints that iteratively optimize spatial arrangements, ensuring a collision-free and accessible layout solution. In the final rendering stage, we propose a novel AnyReach Sampling strategy for camera trajectory, along with the Interval Timestep Flow Sampling (ITFS) strategy, to efficiently optimize the coarse 3D Gaussian scene representation. These approaches help reduce the total generation time to under 30 minutes. Extensive experiments demonstrate that our method can produce geometrically rational 3D indoor scenes, surpassing prior approaches in both rendering speed and visual quality while preserving editability. The code will be available soon. |
| title | RoomPlanner: Explicit Layout Planner for Easier LLM-Driven 3D Room Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.17048 |