Department of Computer Science, Ben-Gurion University of the Negev, PO Box 653, Beer-Sheva 84105, Israel.
IEEE Trans Pattern Anal Mach Intell. 2012 Jul;34(7):1263-80. doi: 10.1109/TPAMI.2011.262. Epub 2011 Dec 27.
Visual curve completion is a fundamental perceptual mechanism that completes the missing parts (e.g., due to occlusion) between observed contour fragments. Previous research into the shape of completed curves has generally followed an "axiomatic" approach, where desired perceptual/geometrical properties are first defined as axioms, followed by mathematical investigation into curves that satisfy them. However, determining psychophysically such desired properties is difficult and researchers still debate what they should be in the first place. Instead, here we exploit the observation that curve completion is an early visual process to formalize the problem in the unit tangent bundle R(2) × S(1), which abstracts the primary visual cortex (V1) and facilitates exploration of basic principles from which perceptual properties are later derived rather than imposed. Exploring here the elementary principle of least action in V1, we show how the problem becomes one of finding minimum-length admissible curves in R(2) × S(1). We formalize the problem in variational terms, we analyze it theoretically, and we formulate practical algorithms for the reconstruction of these completed curves. We then explore their induced visual properties vis-à-vis popular perceptual axioms and show how our theory predicts many perceptual properties reported in the corresponding perceptual literature. Finally, we demonstrate a variety of curve completions and report comparisons to psychophysical data and other completion models.
视觉曲线完成是一种基本的感知机制,它可以完成观察到的轮廓片段之间缺失的部分(例如,由于遮挡)。之前关于完成曲线形状的研究通常遵循一种“公设”方法,其中所需的感知/几何属性首先被定义为公设,然后用数学方法研究满足这些公设的曲线。然而,确定这些所需的属性在心理物理学上是很困难的,研究人员仍然在争论它们首先应该是什么。相反,我们利用曲线完成是一个早期视觉过程的观察,将这个问题在单位切丛 R(2) × S(1) 中形式化,这抽象了初级视觉皮层 (V1),并促进了从基本原理中探索感知属性,而不是强加。在这里探索 V1 中的最小作用量原理,我们展示了如何将问题转化为在 R(2) × S(1) 中寻找最短可接受曲线的问题。我们用变分术语形式化这个问题,从理论上分析它,并为这些完成曲线的重建制定实用算法。然后,我们探讨了它们与流行的感知公理的视觉诱导属性,并展示了我们的理论如何预测感知文献中报告的许多感知属性。最后,我们展示了各种曲线完成,并报告了与心理物理学数据和其他完成模型的比较。