Recovering the Spatial Layout of Cluttered Rooms

被引：227

作者：

Hedau, Varsha ^{[1
]}

Hoiem, Derek ^{[2
]}

Forsyth, David ^{[2
]}

机构：

[1] Univ Illinois, Elect & Comp Engg Dept, Urbana, IL 61801 USA

[2] Univ Illinois, Dept Comp Sci, Chicago, IL 60680 USA

来源：

2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) | 2009年

关键词：

D O I：

10.1109/ICCV.2009.5459411

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, we consider the problem of recovering the spatial layout of indoor scenes from monocular images. The presence of clutter is a major problem for existing single-view 3D reconstruction algorithms, most of which rely on finding the ground-wall boundary. In most rooms, this boundary is partially or entirely occluded. We gain robustness to clutter by modeling the global room space with a parameteric 3D "box" and by iteratively localizing clutter and refitting the box. To fit the box, we introduce a structured learning algorithm that chooses the set of parameters to minimize error, based on global perspective cues. On a dataset of 308 images, we demonstrate the ability of our algorithm to recover spatial layout in cluttered rooms and show several examples of estimated free space.

引用

页码：1849 / 1856

页数：8