Invertible Image Conversion Net, or IICNet, is a generic framework for reversible image conversion tasks. Unlike previous encoder-decoder based methods, IICNet maintains a highly invertible structure based on invertible neural networks (INNs) to better preserve the information during conversion. It uses a relation module and a channel squeeze layer to improve the INN nonlinearity to extract cross-image relations and the network flexibility, respectively.
Source: IICNet: A Generic Framework for Reversible Image ConversionPaper | Code | Results | Date | Stars |
---|
Component | Type |
|
---|---|---|
Affine Coupling
|
Bijective Transformation | |
Invertible 1x1 Convolution
|
Convolutions |