Indoor Segmentation and Support Inference from RGBD Images

被引：3094

作者：

Silberman, Nathan ^{[1
]}

Hoiem, Derek ^{[2
]}

Kohli, Pushmeet ^{[3
]}

Fergus, Rob ^{[1
]}

机构：

[1] NYU, Courant Inst, New York, NY 10003 USA

[2] Univ Illinois, Dept Comp Sci, Urbana, IL USA

[3] Microsoft Res, Cambridge, England

来源：

COMPUTER VISION - ECCV 2012, PT V | 2012年 / 7576卷

基金：

美国国家科学基金会;

关键词：

D O I：

10.1007/978-3-642-33715-4_54

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present an approach to interpret the major surfaces, objects, and support relations of an indoor scene from an RGBD image. Most existing work ignores physical interactions or is applied only to tidy rooms and hallways. Our goal is to parse typical, often messy, indoor scenes into floor, walls, supporting surfaces, and object regions, and to recover support relationships. One of our main interests is to better understand how 3D cues can best inform a structured 3D interpretation. We also contribute a novel integer programming formulation to infer physical support relations. We offer a new dataset of 1449 RGBD images, capturing 464 diverse indoor scenes, with detailed annotations. Our experiments demonstrate our ability to infer support relations in complex scenes and verify that our 3D scene cues and inferred support lead to better object segmentation.

引用

页码：746 / 760

页数：15