Estimating the 3D Layout of Indoor Scenes and Its Clutter from Depth Sensors

2013 IEEE International Conference on Computer Vision Pub Date : 2013-12-01 DOI:10.1109/ICCV.2013.161

Jian Zhang, Chen Kan, A. Schwing, R. Urtasun

引用次数: 78

Abstract

In this paper we propose an approach to jointly estimate the layout of rooms as well as the clutter present in the scene using RGB-D data. Towards this goal, we propose an effective model that is able to exploit both depth and appearance features, which are complementary. Furthermore, our approach is efficient as we exploit the inherent decomposition of additive potentials. We demonstrate the effectiveness of our approach on the challenging NYU v2 dataset and show that employing depth reduces the layout error by 6% and the clutter estimation by 13%.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于深度传感器的室内场景三维布局及其杂波估计

在本文中，我们提出了一种利用RGB-D数据联合估计房间布局以及场景中存在的杂波的方法。为了实现这一目标，我们提出了一个有效的模型，能够利用深度和外观特征，这是互补的。此外，我们的方法是有效的，因为我们利用了加性势的固有分解。我们在具有挑战性的NYU v2数据集上证明了我们的方法的有效性，并表明使用深度将布局误差降低了6%，杂波估计降低了13%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

2013 IEEE International Conference on Computer Vision

自引率

0.00%

发文量

期刊最新文献

PixelTrack: A Fast Adaptive Algorithm for Tracking Non-rigid Objects A General Dense Image Matching Framework Combining Direct and Feature-Based Costs Latent Space Sparse Subspace Clustering Non-convex P-Norm Projection for Robust Sparsity Hierarchical Joint Max-Margin Learning of Mid and Top Level Representations for Visual Recognition