Paper Info
Title
Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize.
Abstract
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.
Year
Venue
Field
2017
arXiv: Computer Vision and Pattern Recognition
Computer science,Deconvolution,Theoretical computer science,Artificial intelligence,Kernel (image processing),Pattern recognition,Convolution,Algorithm,Pixel,Initialization,Overlap–add method,Line integral convolution,Computational complexity theory
DocType
Volume
Citations 
Journal
abs/1707.02937
5
PageRank 
References 
Authors
0.45
0
6
Name
Order
Citations
PageRank
andrew aitken13378.57
Christian Ledig248927.08
Theis, Lucas336825.90
Jose Caballero466322.59
Zehan Wang536911.51
Wenzhe Shi679239.85