论文标题
Relu Fields：可能的非线性
ReLU Fields: The Little Non-linearity That Could
论文作者
论文摘要
在最近的许多作品中，多层感知（MLP）已被证明适合对复杂的空间变化功能进行建模，包括图像和3D场景。尽管MLP能够以前所未有的质量和记忆足迹来表示复杂的场景，但是MLP的这种表达力是以长期培训和推理时间为代价的。另一方面，基于常规网格的表示上的双线性/三线性插值可以给出快速训练和推理时间，但不需要大量额外的内存就无法匹配MLP的质量。因此，在这项工作中，我们调查了基于网格的表示的最小变化是什么，这些变化允许在启用快速重建和渲染时间的同时保留MLP的高保真度结果。我们引入了一个令人惊讶的简单更改，可以实现此任务 - 仅允许在插值网格值上固定非线性（relu）。当结合粗表结优化的优化时，我们表明这种方法与最先进的方法具有竞争力。我们报告了辐射领域和占用场的结果，并与多种现有替代方案进行了比较。本文的代码和数据可在https://geometry.cs.ucl.ac.uk/projects/2022/relu_fields获得。
In many recent works, multi-layer perceptions (MLPs) have been shown to be suitable for modeling complex spatially-varying functions including images and 3D scenes. Although the MLPs are able to represent complex scenes with unprecedented quality and memory footprint, this expressive power of the MLPs, however, comes at the cost of long training and inference times. On the other hand, bilinear/trilinear interpolation on regular grid based representations can give fast training and inference times, but cannot match the quality of MLPs without requiring significant additional memory. Hence, in this work, we investigate what is the smallest change to grid-based representations that allows for retaining the high fidelity result of MLPs while enabling fast reconstruction and rendering times. We introduce a surprisingly simple change that achieves this task -- simply allowing a fixed non-linearity (ReLU) on interpolated grid values. When combined with coarse to-fine optimization, we show that such an approach becomes competitive with the state-of-the-art. We report results on radiance fields, and occupancy fields, and compare against multiple existing alternatives. Code and data for the paper are available at https://geometry.cs.ucl.ac.uk/projects/2022/relu_fields.
