3D shapes provide substantially more information than 2D images. However, the acquisition of 3D shapes is sometimes very difficult or even impossible in comparison with acquiring 2D images, making it necessary to derive the 3D shape from 2D images. Although this is, in general, a mathematically ill-posed problem, it might be solved by constraining the problem formulation using prior information. Here, we present a new approach based on Kendall's shape space to reconstruct 3D shapes from single monocular 2D images. The work is motivated by an application to study the feeding behavior of the basking shark, an endangered species whose massive size and mobility render 3D shape data nearly impossible to obtain, hampering understanding of their feeding behaviors and ecology. 2D images of these animals in feeding position, however, are readily available. We compare our approach with state-of-the-art shape-based approaches, both on human stick models and on shark head skeletons. Using a small set of training shapes, we show that the Kendall shape space approach is substantially more robust than previous methods and results in plausible shapes. This is essential for the motivating application in which specimens are rare and therefore only few training shapes are available.
翻译:3D 形状比 2D 图像提供的信息要多得多。 然而, 获取 3D 形状有时非常困难, 甚至不可能与获取 2D 图像相比, 获取 3D 形状有时非常困难, 使得有必要从 2D 图像中获取 3D 形状。 虽然一般来说这是一个数学错误的问题, 但它可能通过使用先前的信息来限制问题配制来解决 。 在此, 我们展示了基于 Kendall 形状空间的新方法, 以重建 3D 形状, 以单个单单立体 2D 图像 。 这项工作的动机是使用一种应用来研究 烤鲨 的喂养行为, 这种濒危鲨鱼的大小和流动性使 3D 形状的数据几乎无法获得, 从而妨碍了对它们喂养行为和生态学的理解。 然而, 这对于这些处于喂养位置的动物来说, 2D 图像是很容易找到的。 我们比较了我们的方法与以最先进的形状为基础的方法,, 包括人类粘托模型和鲨鱼头骨。 使用一套小的培训形状, 我们显示 Kendall 塑造空间 方法比以前的方法和结果要大得多, 强得多,, 并且以 和结果 。