arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1407.3840cs.CV
收藏

稀疏样本深度重建:表示、算法和采样

Depth Reconstruction from Sparse Samples: Representation, Algorithm, and Sampling

University of California at San Diego(加州大学圣迭戈分校);Purdue University(普渡大学)

Lee-Kang Liu, Stanley H. Chan, Truong Q. Nguyen

摘要:

三维技术和计算机视觉应用的快速发展,推动了深度获取和估计方法的发展。然而,现有的大多数硬件和软件方法由于深度精度差、分辨率低和计算成本高而性能有限。在本文中,我们提出了一种计算效率高的方法来恢复密集的深度图从稀疏的测量。我们做了三个贡献。首先,我们提供的经验证据表明,深度图可以编码更稀疏比自然图像使用常见的字典,如小波和contourlet。我们还表明,一个组合的小波-轮廓波字典实现更好的性能比单独使用字典。其次,我们提出了交替方向的乘法器(ADMM),以实现快速重建。提出了一种多尺度温启动方法,以加快收敛速度。第三,我们提出了一个两阶段的随机抽样方案,以最佳选择的采样位置,从而最大限度地提高重建性能,为任何给定的采样预算。实验结果表明,该方法产生高质量的密集深度估计,并对噪声测量具有鲁棒性。在立体匹配的实际数据的应用程序进行了演示。

英文摘要:

The rapid development of 3D technology and computer vision applications have motivated a thrust of methodologies for depth acquisition and estimation. However, most existing hardware and software methods have limited performance due to poor depth precision, low resolution and high computational cost. In this paper, we present a computationally efficient method to recover dense depth maps from sparse measurements. We make three contributions. First, we provide empirical evidence that depth maps can be encoded much more sparsely than natural images by using common dictionaries such as wavelets and contourlets. We also show that a combined wavelet-contourlet dictionary achieves better performance than using either dictionary alone. Second, we propose an alternating direction method of multipliers (ADMM) to achieve fast reconstruction. A multi-scale warm start procedure is proposed to speed up the convergence. Third, we propose a two-stage randomized sampling scheme to optimally choose the sampling locations, thus maximizing the reconstruction performance for any given sampling budget. Experimental results show that the proposed method produces high quality dense depth estimates, and is robust to noisy measurements. Applications to real data in stereo matching are demonstrated.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑