构建合成数据集Room Envelopes，助力从图像重建室内完整结构布局。
Room Envelopes: A Synthetic Dataset for Indoor Layout Reconstruction from Images
- 基于合成图像与双点云标注，支持单目几何估计直接监督。
- 可同时预测可见表面与结构布局，提升场景完整性理解。
- 适合关注室内重建、几何推理的开发者与研究者。
当前场景重建方法虽能准确恢复图像中可见的3D表面，但难以还原被遮挡部分。尽管生成模型在基于局部观测重建完整物体上取得进展，但对墙、地、顶等结构性元素的关注仍不足。我们认为这些结构通常呈平面、重复且简单，因此可能适用成本更低的方法。本文提出一个合成数据集Room Envelopes，为每张图像提供RGB图像及两个对应的点云图：一个表示可见表面，另一个表示移除家具后首层结构表面（即结构布局）。该设计使前馈单目几何估计器能够直接获得监督信号，同时预测首个可见表面和首个结构表面，从而实现对场景范围、物体形状与位置的更完整理解。
原文摘要 · Abstract (English)
Modern scene reconstruction methods are able to accurately recover 3D surfaces that are visible in one or more images. However, this leads to incomplete reconstructions, missing all occluded surfaces. While much progress has been made on reconstructing entire objects given partial observations using generative models, the structural elements of a scene, like the walls, floors and ceilings, have received less attention. We argue that these scene elements should be relatively easy to predict, since they are typically planar, repetitive and simple, and so less costly approaches may be suitable. In this work, we present a synthetic dataset -- Room Envelopes -- that facilitates progress on this task by providing a set of RGB images and two associated pointmaps for each image: one capturing the visible surface and one capturing the first surface once fittings and fixtures are removed, that is, the structural layout. As we show, this enables direct supervision for feed-forward monocular geometry estimators that predict both the first visible surface and the first layout surface. This confers an understanding of the scene's extent, as well as the shape and location of its objects.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。