Reality Capture and Digital Twins

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

Valentin Bieri, Marie-Julie Rakotosaona, Keisuke Tateno, Francis Engelmann, Leonidas Guibas

Published 2025

Thumbnail for HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild
📄 Paper🌐 Project💻 Code
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.

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.

Topics

2D floor plan3D Reconstruction3D floor planBIMDatasetFloor Plan Reconstruction and Parametrizationdigital twinslayout recoveryroom segmentation

Cite this paper

@inproceedings{a3af024a,
  title   = {{HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild}},
  author  = {Valentin Bieri and Marie-Julie Rakotosaona and Keisuke Tateno and Francis Engelmann and Leonidas Guibas},
  booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
  year    = {2025}
}