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

Keywords: Scene Layout

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.

Dataset URL: https://huggingface.co/datasets/houselayout3d/HouseLayout3D

Code URL: https://github.com/HouseLayout3D/houselayout3d

Primary Area: Datasets & Benchmarks for applications in computer vision

Submission Number: 2166