论文标题
从数据到函数：您的数据点是一个函数，您可以像对待一个功能
From data to functa: Your data point is a function and you can treat it like one
论文作者
论文摘要
在深度学习中，这是在离散网格上代表世界的衡量标准的常见实践，例如一个像素的2D网格。但是，这些测量所代表的基本信号通常是连续的，例如图像中描绘的场景。然后，强大的连续替代方法是使用隐式神经表示形式表示这些测量，这是一种训练有训练的神经功能，可为任何输入空间位置输出适当的测量值。在本文中，我们将这个想法提升到了一个新的水平：对这些功能进行深入学习，将它们视为数据需要什么？在这种情况下，我们将数据称为函数，并提出了一个有关函数深入学习的框架。该观点围绕从数据到函数的有效转换，函数的紧凑表示以及有效地求解功能上的下游任务围绕着有效的转换提出了许多挑战。我们概述了克服这些挑战的食谱，并将其应用于多种数据模式，包括图像，3D形状，神经辐射场（NERF）和流形数据。我们证明，这种方法在数据模式之间具有各种引人注目的属性，尤其是在生成建模，数据插补，新型视图合成和分类的规范任务上。代码：https：//github.com/deepmind/functa
It is common practice in deep learning to represent a measurement of the world on a discrete grid, e.g. a 2D grid of pixels. However, the underlying signal represented by these measurements is often continuous, e.g. the scene depicted in an image. A powerful continuous alternative is then to represent these measurements using an implicit neural representation, a neural function trained to output the appropriate measurement value for any input spatial location. In this paper, we take this idea to its next level: what would it take to perform deep learning on these functions instead, treating them as data? In this context we refer to the data as functa, and propose a framework for deep learning on functa. This view presents a number of challenges around efficient conversion from data to functa, compact representation of functa, and effectively solving downstream tasks on functa. We outline a recipe to overcome these challenges and apply it to a wide range of data modalities including images, 3D shapes, neural radiance fields (NeRF) and data on manifolds. We demonstrate that this approach has various compelling properties across data modalities, in particular on the canonical tasks of generative modeling, data imputation, novel view synthesis and classification. Code: https://github.com/deepmind/functa
