PLANA3R: 通过前馈平面撒点实现零样本度量平面三维重建
PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting
AI总结：
PLANA3R通过前馈平面撒点实现零样本度量平面三维重建，无需显式平面监督，适用于大规模立体数据集。
摘要：
本文通过利用室内场景固有的几何规律与紧凑表示，解决度量三维重建问题。利用平面3D基元——适用于人工环境的合适表示方式，我们引入PLANA3R，一种无姿态框架的度量平面三维重建方法，从未经姿态的两视角图像中进行重建。我们的方法采用视觉Transformer提取一组稀疏平面基元，估计相对相机姿态，并通过平面撒点进行几何学习监督，其中梯度通过高分辨率渲染的深度和法线图传播。不同于以往前馈方法在训练中需要3D平面标注，PLANA3R在没有显式平面监督的情况下学习平面3D结构，使在大规模立体数据集上进行可扩展训练成为可能，仅使用深度和法线标注。我们在多个室内场景数据集上验证PLANA3R，并在多种任务中展示了对非领域室内环境的良好泛化能力，包括三维表面重建、深度估计和相对姿态估计。此外，通过平面3D表示的建模，我们的方法具备准确平面分割的能力。项目页面可在https://lck666666.github.io/plana3r访问。
英文摘要：
This paper addresses metric 3D reconstruction of indoor scenes by exploiting their inherent geometric regularities with compact representations. Using planar 3D primitives - a well-suited representation for man-made environments - we introduce PLANA3R, a pose-free framework for metric Planar 3D Reconstruction from unposed two-view images. Our approach employs Vision Transformers to extract a set of sparse planar primitives, estimate relative camera poses, and supervise geometry learning via planar splatting, where gradients are propagated through high-resolution rendered depth and normal maps of primitives. Unlike prior feedforward methods that require 3D plane annotations during training, PLANA3R learns planar 3D structures without explicit plane supervision, enabling scalable training on large-scale stereo datasets using only depth and normal annotations. We validate PLANA3R on multiple indoor-scene datasets with metric supervision and demonstrate strong generalization to out-of-domain indoor environments across diverse tasks under metric evaluation protocols, including 3D surface reconstruction, depth estimation, and relative pose estimation. Furthermore, by formulating with planar 3D representation, our method emerges with the ability for accurate plane segmentation. The project page is available at https://lck666666.github.io/plana3r
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
