paper-with-me

Papers

ReLU Fields: The Little Non-linearity That Could

2022-05-22 · Animesh Karnewar, Tobias Ritschel, Oliver Wang, Niloy J. Mitra

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.

📄 PDF Abstract BibTeX arXiv:2205.10824

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Deep Residual Learning in the JPEG Transform Domain

2018-12-31 · ICCV 2019 10 · Max Ehrlich, Larry Davis

We introduce a general method of performing Residual Network inference and learning in the JPEG transform domain that allows the network to consume compressed images as input. Our formulation leverages the linearity of t…

General Classificationimage-classificationImage Classification

Effects of the Nonlinearity in Activation Functions on the Performance of Deep Learning Models

2020-10-14 · Nalinda Kulathunga, Nishath Rajiv Ranasinghe, Daniel Vrinceanu, Zackary Kinsman 외

The nonlinearity of activation functions used in deep learning models are crucial for the success of predictive models. There are several commonly used simple nonlinear functions, including Rectified Linear Unit (ReLU) a…

image-classificationImage ClassificationTransfer Learning

Linearity-based neural network compression

2025-06-26 · Silas Dobler, Florian Lemmerich

In neural network compression, most current methods reduce unnecessary parameters by measuring importance and redundancy. To augment already highly optimized existing solutions, we propose linearity-based compression as …

Efficient Neural NetworkNeural Network Compression

Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference

2023-01-23 · Souvik Kundu, Shunlin Lu, Yuke Zhang, Jacqueline Liu 외

The large number of ReLU non-linearity operations in existing deep neural networks makes them ill-suited for latency-efficient private inference (PI). Existing techniques to reduce ReLU operations often involve manual ef…

Sensitivity

Optimizing Performance of Feedforward and Convolutional Neural Networks through Dynamic Activation Functions

2023-08-10 · Chinmay Rane, Kanishka Tyagi, Michael Manry

Deep learning training training algorithms are a huge success in recent years in many fields including speech, text,image video etc. Deeper and deeper layers are proposed with huge success with resnet structures having a…