Originally designed for applications in computer graphics, visual computing (VC) methods synthesize information about physical and virtual worlds, using prescribed algorithms optimized for spatial computing. VC is used to analyze geometry, physically simulate solids, fluids, and other media, and render the world via optical techniques. These fine-tuned computations that operate explicitly on a given input solve so-called forward problems, VC excels at. By contrast, deep learning (DL) allows for the construction of general algorithmic models, side stepping the need for a purely first principles-based approach to problem solving. DL is powered by highly parameterized neural network architectures -- universal function approximators -- and gradient-based search algorithms which can efficiently search that large parameter space for optimal models. This approach is predicated by neural network differentiability, the requirement that analytic derivatives of a given problem's task metric can be computed with respect to neural network's parameters. Neural networks excel when an explicit model is not known, and neural network training solves an inverse problem in which a model is computed from data.

翻译：视觉计算（VC）方法最初为计算机图形学应用而设计，通过采用针对空间计算优化的预设算法，综合处理物理世界与虚拟世界的信息。VC用于分析几何结构、对固体、流体及其他介质进行物理模拟，并通过光学技术渲染世界。这些针对给定输入显式执行的精细调校计算，能够解决VC所擅长的所谓的正问题。相比之下，深度学习（DL）允许构建通用算法模型，从而规避了完全基于第一性原理求解问题的需求。DL由高度参数化的神经网络架构——通用函数逼近器——以及基于梯度的搜索算法驱动，后者能够高效地在庞大的参数空间中搜索最优模型。这种方法以神经网络可微性为前提，即要求能够针对给定问题的任务度量计算相对于神经网络参数的解析导数。当显式模型未知时，神经网络表现出色，且神经网络的训练本身即为一个从数据中计算模型的逆问题求解过程。