Layout Anything: One Transformer for Universal Room Layout Estimation

TL;DR

Layout Anything introduces a transformer-based framework that unifies geometric structure prediction for indoor room layouts, achieving state-of-the-art accuracy and real-time inference without complex post-processing.

Contribution

The paper adapts the OneFormer's universal segmentation architecture for room layout estimation, integrating novel data augmentation and geometric loss modules for improved performance.

Findings

Achieves state-of-the-art accuracy on multiple benchmarks.

Runs at 114ms inference speed, enabling real-time applications.

Effectively enforces geometric constraints during training.

Abstract

We present Layout Anything, a transformer-based framework for indoor layout estimation that adapts the OneFormer's universal segmentation architecture to geometric structure prediction. Our approach integrates OneFormer's task-conditioned queries and contrastive learning with two key modules: (1) a layout degeneration strategy that augments training data while preserving Manhattan-world constraints through topology-aware transformations, and (2) differentiable geometric losses that directly enforce planar consistency and sharp boundary predictions during training. By unifying these components in an end-to-end framework, the model eliminates complex post-processing pipelines while achieving high-speed inference at 114ms. Extensive experiments demonstrate state-of-the-art performance across standard benchmarks, with pixel error (PE) of 5.43% and corner error (CE) of 4.02% on the LSUN, PE of 7.04% (CE 5.17%) on the Hedau and PE of 4.03% (CE 3.15%) on the Matterport3D-Layout datasets. The framework's combination of geometric awareness and computational efficiency makes it particularly suitable for augmented reality applications and large-scale 3D scene reconstruction tasks.