CUF: Continuous Upsampling Filters

10/13/2022
by   Cristina Vasconcelos, et al.
0

Neural fields have rapidly been adopted for representing 3D signals, but their application to more classical 2D image-processing has been relatively limited. In this paper, we consider one of the most important operations in image processing: upsampling. In deep learning, learnable upsampling layers have extensively been used for single image super-resolution. We propose to parameterize upsampling kernels as neural fields. This parameterization leads to a compact architecture that obtains a 40-fold reduction in the number of parameters when compared with competing arbitrary-scale super-resolution architectures. When upsampling images of size 256x256 we show that our architecture is 2x-10x more efficient than competing arbitrary-scale super-resolution architectures, and more efficient than sub-pixel convolutions when instantiated to a single-scale model. In the general setting, these gains grow polynomially with the square of the target scale. We validate our method on standard benchmarks showing such efficiency gains can be achieved without sacrifices in super-resolution performance.

READ FULL TEXT

page 2

page 4

page 7

page 12

page 14

page 15

research
06/16/2022

Real-World Single Image Super-Resolution Under Rainy Condition

Image super-resolution is an important research area in computer vision ...
research
03/08/2023

QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms

In this work, we present QuickSRNet, an efficient super-resolution archi...
research
09/18/2020

AdderSR: Towards Energy Efficient Image Super-Resolution

This paper studies the single image super-resolution problem using adder...
research
01/28/2022

Deep Networks for Image and Video Super-Resolution

Efficiency of gradient propagation in intermediate layers of convolution...
research
02/16/2021

Selfie Periocular Verification using an Efficient Super-Resolution Approach

Selfie-based biometrics has great potential for a wide range of applicat...
research
12/06/2018

Binary Document Image Super Resolution for Improved Readability and OCR Performance

There is a need for information retrieval from large collections of low-...
research
12/08/2017

A Frequency Domain Neural Network for Fast Image Super-resolution

In this paper, we present a frequency domain neural network for image su...

Please sign up or login with your details

Forgot password? Click here to reset