Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.02450 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915648286752768 |
|---|---|
| author | Bieri, Valentin Rakotosaona, Marie-Julie Tateno, Keisuke Engelmann, Francis Guibas, Leonidas |
| author_facet | Bieri, Valentin Rakotosaona, Marie-Julie Tateno, Keisuke Engelmann, Francis Guibas, Leonidas |
| contents | Current 3D layout estimation models are primarily trained on synthetic datasets containing simple single room or single floor environments. As a consequence, they cannot natively handle large multi floor buildings and require scenes to be split into individual floors before processing, which removes global spatial context that is essential for reasoning about structures such as staircases that connect multiple levels. In this work, we introduce HouseLayout3D, a real world benchmark designed to support progress toward full building scale layout estimation, including multiple floors and architecturally intricate spaces. We also present MultiFloor3D, a simple training free baseline that leverages recent scene understanding methods and already outperforms existing 3D layout estimation models on both our benchmark and prior datasets, highlighting the need for further research in this direction. Data and code are available at: https://houselayout3d.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_02450 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild Bieri, Valentin Rakotosaona, Marie-Julie Tateno, Keisuke Engelmann, Francis Guibas, Leonidas Computer Vision and Pattern Recognition Artificial Intelligence Current 3D layout estimation models are primarily trained on synthetic datasets containing simple single room or single floor environments. As a consequence, they cannot natively handle large multi floor buildings and require scenes to be split into individual floors before processing, which removes global spatial context that is essential for reasoning about structures such as staircases that connect multiple levels. In this work, we introduce HouseLayout3D, a real world benchmark designed to support progress toward full building scale layout estimation, including multiple floors and architecturally intricate spaces. We also present MultiFloor3D, a simple training free baseline that leverages recent scene understanding methods and already outperforms existing 3D layout estimation models on both our benchmark and prior datasets, highlighting the need for further research in this direction. Data and code are available at: https://houselayout3d.github.io. |
| title | HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2512.02450 |