预训练模型时代下的非摆拍稀疏视角房间布局重建

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

February 24, 2025

作者: Yaxuan Huang, Xili Dai, Jianan Wang, Xianbiao Qi, Yixing Yuan, Xiangyu Yue

cs.AI

摘要

由于多视角几何带来的复杂性，从多视角图像进行房间布局估计的研究尚不充分，这通常需要多步骤解决方案，如相机内外参数估计、图像匹配和三角测量。然而，在三维重建领域，近期三维基础模型（如DUSt3R）的进展，已将从传统的多步骤运动恢复结构（Structure-from-Motion）流程转向了端到端的单步方法。为此，我们提出了Plane-DUSt3R，一种利用三维基础模型DUSt3R进行多视角房间布局估计的新方法。Plane-DUSt3R整合了DUSt3R框架，并在房间布局数据集（Structure3D）上进行了微调，调整目标以估计结构平面。通过生成统一且简洁的结果，Plane-DUSt3R仅需一个后处理步骤和二维检测结果即可完成房间布局估计。与以往依赖单视角或全景图像的方法不同，Plane-DUSt3R扩展了处理多视角图像的场景。此外，它提供了一个简化的端到端解决方案，简化了流程并减少了误差累积。实验结果表明，Plane-DUSt3R不仅在合成数据集上超越了现有最先进方法，还在包含不同图像风格（如卡通）的真实数据上展现了其鲁棒性和有效性。我们的代码已公开于：https://github.com/justacar/Plane-DUSt3R。

English

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