arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.08657cs.CVcs.LGeess.IV
收藏

遮挡场:非视线曲面重建的隐式表示

Occlusion Fields: An Implicit Representation for Non-Line-of-Sight Surface Reconstruction

University of Bonn(波恩大学);Delft University of Technology(代尔夫特理工大学)

Javier Grau, Markus Plack, Patrick Haehn, Michael Weinmann, Matthias Hullin

摘要:

非视线重建(NLoS)是一种新型的间接成像方式,其目的是从直接可见的漫射壁间接散射的光的测量中恢复视场外的物体或场景部分。尽管最近的进展,在收购和重建技术,适定性的问题,特别是对象及其形状的可恢复性,仍然是一个悬而未决的问题。通常采用的费马路径准则在这方面是相当保守的,因为它将一些表面分类为不可恢复的,尽管它们对信号有贡献。在本文中,我们使用一个更简单的必要条件不透明的表面补丁是可恢复的。这样的一片表面必须从墙上的某个点直接可见,并且它必须遮挡其后面的空间。受神经隐式表征最新进展的启发,我们设计了一种新的NLoS场景表示和重建技术,将可恢复性的治疗与重建本身结合起来。我们的方法,我们验证各种合成和实验数据集,表现出有趣的属性。与内存效率低下的体积表示,我们允许推断自适应镶嵌表面的飞行时间测量的中等分辨率。它可以进一步恢复超出费马路径标准的特征,并且对大量的自遮挡具有鲁棒性。我们认为,这是第一次在一个系统中实现这些属性,作为一个额外的好处,它是可训练的,因此适合数据驱动的方法。

英文摘要:

Non-line-of-sight reconstruction (NLoS) is a novel indirect imaging modality that aims to recover objects or scene parts outside the field of view from measurements of light that is indirectly scattered off a directly visible, diffuse wall. Despite recent advances in acquisition and reconstruction techniques, the well-posedness of the problem at large, and the recoverability of objects and their shapes in particular, remains an open question. The commonly employed Fermat path criterion is rather conservative with this regard, as it classifies some surfaces as unrecoverable, although they contribute to the signal. In this paper, we use a simpler necessary criterion for an opaque surface patch to be recoverable. Such piece of surface must be directly visible from some point on the wall, and it must occlude the space behind itself. Inspired by recent advances in neural implicit representations, we devise a new representation and reconstruction technique for NLoS scenes that unifies the treatment of recoverability with the reconstruction itself. Our approach, which we validate on various synthetic and experimental datasets, exhibits interesting properties. Unlike memory-inefficient volumetric representations, ours allows to infer adaptively tessellated surfaces from time-of-flight measurements of moderate resolution. It can further recover features beyond the Fermat path criterion, and it is robust to significant amounts of self-occlusion. We believe that this is the first time that these properties have been achieved in one system that, as an additional benefit, is trainable and hence suited for data-driven 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。

↑