Neural networks (NN) for single-view 3D reconstruction (SVR) have gained in popularity. Recent work points out that for SVR, most cutting-edge NNs have limited performance on reconstructing unseen objects because they rely primarily on recognition (i.e., classification-based methods) rather than shape reconstruction. To understand this issue in depth, we provide a systematic study on when and why NNs prefer recognition to reconstruction and vice versa. Our finding shows that a leading factor in determining recognition versus reconstruction is how dispersed the training data is. Thus, we introduce the dispersion score, a new data-driven metric, to quantify this leading factor and study its effect on NNs. We hypothesize that NNs are biased toward recognition when training images are more dispersed and training shapes are less dispersed. Our hypothesis is supported and the dispersion score is proved effective through our experiments on synthetic and benchmark datasets. We show that the proposed metric is a principal way to analyze reconstruction quality and provides novel information in addition to the conventional reconstruction score.
翻译:用于单一视角的3D重建(SVR)的神经网络(NN)越来越受欢迎。最近的工作指出,对于SVR来说,大多数尖端的NNP在重建无形物体方面表现有限,因为它们主要依靠承认(即基于分类的方法)而不是形状重建。为了深入了解这一问题,我们提供了系统研究,说明NNP在何时和为什么更倾向于承认重建,反之亦然。我们的调查结果表明,确定承认与重建之间的一个主导因素是培训数据是如何分散的。因此,我们引入了分散评分,即新的数据驱动计量,以量化这一主导因素,并研究其对NNP的影响。我们假设,当培训图像更加分散,培训形状不那么分散时,NNP偏重于承认。我们的假设得到支持,分散评分通过我们关于合成和基准数据集的实验证明有效。我们表明,拟议的指标是分析重建质量的主要方法,除了常规重建评分之外,还提供新的信息。