HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild

Abstract

Current 3D layout estimation models are predominantly trained on synthetic datasets biased toward simplistic, single-floor scenes. This prevents them from generalizing to complex, multi-floor buildings, often forcing a per-floor processing approach that sacrifices global context. Few works have attempted to holistically address multi-floor layouts. In this work, we introduce HouseLayout3D, a real-world benchmark dataset, which highlights the limitations of existing research when handling expansive, architecturally complex spaces. Additionally, we propose MultiFloor3D, a baseline method leveraging recent advances in 3D reconstruction and 2D segmentation. Our approach significantly outperforms state-of-the-art methods on both our new and existing datasets. Remarkably, it does not require any layout-specific training.

Cite

Text

Bieri et al. "HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild." Advances in Neural Information Processing Systems, 2025.

Markdown

[Bieri et al. "HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild." Advances in Neural Information Processing Systems, 2025.](https://mlanthology.org/neurips/2025/bieri2025neurips-houselayout3d/)

BibTeX

@inproceedings{bieri2025neurips-houselayout3d,
  title     = {{HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild}},
  author    = {Bieri, Valentin and Rakotosaona, Marie-Julie and Tateno, Keisuke and Engelmann, Francis and Guibas, Leonidas},
  booktitle = {Advances in Neural Information Processing Systems},
  year      = {2025},
  url       = {https://mlanthology.org/neurips/2025/bieri2025neurips-houselayout3d/}
}