arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1901.01535cs.CV
收藏

RayNet:使用射线电位学习体积3D重建

RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials

MPI for Intelligent Systems(马克斯·普朗克智能系统研究所);Max Planck ETH Center for Learning Systems(马克斯·普朗克-ETH学习系统中心);Microsoft(微软);ETH Zürich(苏黎世联邦理工学院);KU Leuven(鲁汶大学)

Despoina Paschalidou, Ali Osman Ulusoy, Carolin Schmitt, Luc van Gool, Andreas Geiger

摘要:

在本文中,我们考虑的问题,重建一个密集的三维模型,使用从不同的角度拍摄的图像。最近基于卷积神经网络(CNN)的方法允许从数据中学习整个任务。然而,它们不包含图像形成的物理学,例如透视几何和遮挡。相反,经典的方法基于马尔可夫随机场(MRF)与射线势明确地模拟这些物理过程,但他们不能处理大的表面外观变化在不同的观点。在本文中,我们提出了RayNet,它结合了这两个框架的优势。RayNet集成了一个学习视图不变特征表示的CNN和一个明确编码透视投影和遮挡物理的MRF。我们使用经验风险最小化来训练RayNet端到端。我们彻底评估了我们在具有挑战性的真实世界数据集上的方法,并展示了它在分段训练基线,手工制作模型以及其他基于学习的方法上的优势。

英文摘要:

In this paper, we consider the problem of reconstructing a dense 3D model using images captured from different views. Recent methods based on convolutional neural networks (CNN) allow learning the entire task from data. However, they do not incorporate the physics of image formation such as perspective geometry and occlusion. Instead, classical approaches based on Markov Random Fields (MRF) with ray-potentials explicitly model these physical processes, but they cannot cope with large surface appearance variations across different viewpoints. In this paper, we propose RayNet, which combines the strengths of both frameworks. RayNet integrates a CNN that learns view-invariant feature representations with an MRF that explicitly encodes the physics of perspective projection and occlusion. We train RayNet end-to-end using empirical risk minimization. We thoroughly evaluate our approach on challenging real-world datasets and demonstrate its benefits over a piece-wise trained baseline, hand-crafted models as well as other learning-based approaches.

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。

↑