【SIGGRAPH Asia 2012专题*技术论文】积累室内场景理解的分类搜索方法

.

【SIGGRAPH Asia 2012专题*技术论文】

积累室内场景理解的分类搜索方法

A Search-Classify Approach for Cluttered Indoor Scene Understanding

Liangliang Nan, Ke Xie, Andrei Sharf




摘要：我们提出一个算法识别和重建三维扫描室内场景。三维室内重建是特别具有挑战性，由于物体的干扰，闭塞和重叠，产生不完整但非常复杂的场景安排。因为它是难以组装成完整的模型扫描部分，传统方法的目标识别和重建就嫌fi系数。我们提出一个方法，search-classify交错分割和分类fi阳离子在迭代的方式。利用强大的分类fi呃我们遍历场景和逐渐传播fi阳离子信息分类。我们加强班fi阳离子模板fi消光的步骤，产生一个场景重建。我们deform-to -fi模板来分类的对象分类fi解决fi阳离子含糊。由此产生的重建是一个近似捕捉一般场景布置。我们的研究结果表明成功的经典fi阳离子和重建杂乱的室内场景，在短短几分钟。
We present an algorithm for recognition and recons***ction of scanned 3D indoor scenes. 3D indoor recons***ction is particularly challenging due to object interferences, occlusions and overlapping which yield incomplete yet very complex scene arrangements. Since it is hard to assemble scanned segments into complete models,traditional methods for object recognition and recons***ction would be inefficient. We present a search-classify approach which interleaves segmentation and classification in an iterative manner. Using a robust classifier we traverse the scene and gradually propagate classification information. We reinforce classification by a template fitting step which yields a scene recons***ction. We deform-to-fit templates to classified objects to resolve classification ambiguities.The resulting recons***ction is an approximation which captures the general scene arrangement. Our results demonstrate successful classification and recons***ction of cluttered indoor scenes, captured in just few minutes.
要了解该论文的详情呢，就下载附件好好研究一下哈~更多新技术分享尽在web3D纳金网http://www.narkii.com/