Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model

TL;DR

This paper introduces Plane-DUSt3R, an end-to-end method leveraging 3D foundation models for multi-view room layout estimation, simplifying the process and outperforming previous approaches on synthetic and real-world data.

Contribution

It presents Plane-DUSt3R, a novel approach that fine-tunes DUSt3R for multi-view room layout estimation, extending capabilities to multiple perspectives with a streamlined, single-step process.

Findings

Outperforms state-of-the-art methods on synthetic datasets.

Demonstrates robustness on in-the-wild data with different styles.

Enables room layout estimation with only 2D detection results.

Abstract

Room layout estimation from multiple-perspective images is poorly investigated due to the complexities that emerge from multi-view geometry, which requires muti-step solutions such as camera intrinsic and extrinsic estimation, image matching, and triangulation. However, in 3D reconstruction, the advancement of recent 3D foundation models such as DUSt3R has shifted the paradigm from the traditional multi-step structure-from-motion process to an end-to-end single-step approach. To this end, we introduce Plane-DUSt3R, a novel method for multi-view room layout estimation leveraging the 3D foundation model DUSt3R. Plane-DUSt3R incorporates the DUSt3R framework and fine-tunes on a room layout dataset (Structure3D) with a modified objective to estimate structural planes. By generating uniform and parsimonious results, Plane-DUSt3R enables room layout estimation with only a single post-processing step and 2D detection results. Unlike previous methods that rely on single-perspective or panorama image, Plane-DUSt3R extends the setting to handle multiple-perspective images. Moreover, it offers a streamlined, end-to-end solution that simplifies the process and reduces error accumulation. Experimental results demonstrate that Plane-DUSt3R not only outperforms state-of-the-art methods on the synthetic dataset but also proves robust and effective on in the wild data with different image styles such as cartoon. Our code is available at: https://github.com/justacar/Plane-DUSt3R