Prim2Room: Layout-Controllable Room Mesh Generation from Primitives
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914943883804672 |
|---|---|
| author | Feng, Chengzeng Wei, Jiacheng Chen, Cheng Li, Yang Ji, Pan Liu, Fayao Li, Hongdong Lin, Guosheng |
| author_facet | Feng, Chengzeng Wei, Jiacheng Chen, Cheng Li, Yang Ji, Pan Liu, Fayao Li, Hongdong Lin, Guosheng |
| contents | We propose Prim2Room, a novel framework for controllable room mesh generation leveraging 2D layout conditions and 3D primitive retrieval to facilitate precise 3D layout specification. Diverging from existing methods that lack control and precision, our approach allows for detailed customization of room-scale environments. To overcome the limitations of previous methods, we introduce an adaptive viewpoint selection algorithm that allows the system to generate the furniture texture and geometry from more favorable views than predefined camera trajectories. Additionally, we employ non-rigid depth registration to ensure alignment between generated objects and their corresponding primitive while allowing for shape variations to maintain diversity. Our method not only enhances the accuracy and aesthetic appeal of generated 3D scenes but also provides a user-friendly platform for detailed room design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_05380 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Prim2Room: Layout-Controllable Room Mesh Generation from Primitives Feng, Chengzeng Wei, Jiacheng Chen, Cheng Li, Yang Ji, Pan Liu, Fayao Li, Hongdong Lin, Guosheng Computer Vision and Pattern Recognition We propose Prim2Room, a novel framework for controllable room mesh generation leveraging 2D layout conditions and 3D primitive retrieval to facilitate precise 3D layout specification. Diverging from existing methods that lack control and precision, our approach allows for detailed customization of room-scale environments. To overcome the limitations of previous methods, we introduce an adaptive viewpoint selection algorithm that allows the system to generate the furniture texture and geometry from more favorable views than predefined camera trajectories. Additionally, we employ non-rigid depth registration to ensure alignment between generated objects and their corresponding primitive while allowing for shape variations to maintain diversity. Our method not only enhances the accuracy and aesthetic appeal of generated 3D scenes but also provides a user-friendly platform for detailed room design. |
| title | Prim2Room: Layout-Controllable Room Mesh Generation from Primitives |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.05380 |