Birds of a Feather: Capturing Avian Shape Models from Images
Birds of a Feather: Capturing Avian Shape Models from Images
复制标题
DOI：
10.1109/cvpr46437.2021.01450
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Yufu Wang;Nikos Kolotouros;Kostas Daniilidis;M. Badger
中科院分区：
文献类型：
--
作者：
Yufu Wang;Nikos Kolotouros;Kostas Daniilidis;M. Badger
动物的形状多种多样，但由于缺乏3D数据，为新物种构建可变形形状模型并不总是可能的。我们提出了一种方法来捕捉新的物种，使用一个明确的模板和该物种的图像。在这方面，我们主要关注鸟类。虽然鸟类的物种数量几乎是哺乳动物的两倍，但没有精确的形状模型。为了捕获新物种，我们首先将铰接模板与每个训练样本相匹配。通过解开姿势和形状，我们学习了一个形状空间，可以从图像证据中捕捉物种之间和每个物种内部的变化。我们从CUB数据集学习多个物种的模型，并提供新的物种特异性和多物种形状模型，这些模型对下游重建任务很有用。使用低维嵌入，我们表明，我们学到的3D形状空间更好地反映了鸟类之间的系统发育关系比学到的感知功能。
Animals are diverse in shape, but building a deformable shape model for a new species is not always possible due to the lack of 3D data. We present a method to capture new species using an articulated template and images of that species. In this work, we focus mainly on birds. Although birds represent almost twice the number of species as mammals, no accurate shape model is available. To capture a novel species, we first fit the articulated template to each training sample. By disentangling pose and shape, we learn a shape space that captures variation both among species and within each species from image evidence. We learn models of multiple species from the CUB dataset, and contribute new species-specific and multi-species shape models that are useful for downstream reconstruction tasks. Using a low-dimensional embedding, we show that our learned 3D shape space better reflects the phylogenetic relationships among birds than learned perceptual features.