ReLU Fields: The Little Non-linearity That Could
ReLU Fields: The Little Non-linearity That Could
复制标题
DOI：
10.1145/3528233.3530707
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
Animesh Karnewar;Tobias Ritschel;Oliver Wang;N. Mitra
中科院分区：
文献类型：
--
作者：
Animesh Karnewar;Tobias Ritschel;Oliver Wang;N. Mitra
在最近的许多工作中，多层感知（MLP）已被证明是适合于建模复杂的空间变化的功能，包括图像和3D场景。虽然MLP能够以前所未有的质量和内存占用来表示复杂场景，但是MLP的这种表达能力是以长时间的训练和推理为代价的。另一方面，基于规则网格表示的双线性/三线性插值可以提供快速的训练和推理时间，但无法在不需要大量额外内存的情况下匹配MLP的质量。因此，在这项工作中，我们调查什么是最小的变化，以网格为基础的表示，允许保留MLP的高保真度的结果，同时实现快速重建和渲染时间。我们引入了一个令人惊讶的简单变化来实现这一任务-简单地允许内插网格值上的固定非线性（ReLU）。当结合粗到细的优化，我们表明，这样的方法变得具有竞争力的国家的最先进的。我们报告结果的辐射场，和占用字段，并与多个现有的替代品进行比较。该论文的代码和数据可在https://geometry.cs.ucl.ac.uk/projects/2022/relu_fields上获取。
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.