Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize

07/10/2017
by   Andrew Aitken, et al.
0

The most prominent problem associated with the deconvolution layer is the presence of checkerboard artifacts in output images and dense labels. To combat this problem, smoothness constraints, post processing and different architecture designs have been proposed. Odena et al. highlight three sources of checkerboard artifacts: deconvolution overlap, random initialization and loss functions. In this note, we proposed an initialization method for sub-pixel convolution known as convolution NN resize. Compared to sub-pixel convolution initialized with schemes designed for standard convolution kernels, it is free from checkerboard artifacts immediately after initialization. Compared to resize convolution, at the same computational complexity, it has more modelling power and converges to solutions with smaller test errors.

READ FULL TEXT

Authors

page 9

page 10

page 11

page 12

page 13

page 14

page 15

page 16

09/22/2016

Is the deconvolution layer the same as a convolutional layer?

In this note, we want to focus on aspects related to two questions most ...
07/15/2021

An Energy-Efficient Edge Computing Paradigm for Convolution-based Image Upsampling

A novel energy-efficient edge computing paradigm is proposed for real-ti...
02/21/2017

Convolution Aware Initialization

Initialization of parameters in deep neural networks has been shown to h...
05/29/2020

A Unified Hardware Architecture for Convolutions and Deconvolutions in CNN

In this paper, a scalable neural network hardware architecture for image...
11/15/2016

One-to-Many Network for Visually Pleasing Compression Artifacts Reduction

We consider the compression artifacts reduction problem, where a compres...
07/31/2016

An exact, cache-localized algorithm for the sub-quadratic convolution of hypercubes

Fast multidimensional convolution can be performed naively in quadratic ...
03/30/2020

A Sampling Theorem for Deconvolution in Two Dimensions

This work studies the problem of estimating a two-dimensional superposit...

Code Repositories

ICNR

Convolution NN resize initialization for subpixel convolutions


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.