论文标题
用于球形图像和表面的插值selectionconv
Interpolated SelectionConv for Spherical Images and Surfaces
论文作者
论文摘要
我们提出了一个新的通用框架，用于在球形（或全向）图像上进行卷积神经网络操作。我们的方法表示表面是不依赖特定采样策略的连接点的图表。此外，通过使用插值的SelectionConv版本，我们可以在使用现有的2D CNN及其权重的同时在球体上操作。由于我们的方法利用了现有的图形实现，因此它也很快并且可以有效地进行微调。我们的方法也足够通用，可以应用于任何表面类型，即使是拓扑不是简单的表面类型。我们证明了我们技术对样式转移和细分的任务的有效性，以及3D网格的风格化。我们提供了各种球形抽样策略的性能的彻底消融研究。
We present a new and general framework for convolutional neural network operations on spherical (or omnidirectional) images. Our approach represents the surface as a graph of connected points that doesn't rely on a particular sampling strategy. Additionally, by using an interpolated version of SelectionConv, we can operate on the sphere while using existing 2D CNNs and their weights. Since our method leverages existing graph implementations, it is also fast and can be fine-tuned efficiently. Our method is also general enough to be applied to any surface type, even those that are topologically non-simple. We demonstrate the effectiveness of our technique on the tasks of style transfer and segmentation for spheres as well as stylization for 3D meshes. We provide a thorough ablation study of the performance of various spherical sampling strategies.
