CollaGAN : Collaborative GAN for Missing Image Data Imputation
This addresses bias in applications requiring multiple image inputs, though it is incremental as it builds on GAN-based approaches.
The paper tackles the problem of missing image data imputation by proposing CollaGAN, a framework that converts it into a multi-domain image-to-image translation task, resulting in images with higher visual quality compared to existing methods.
In many applications requiring multiple inputs to obtain a desired output, if any of the input data is missing, it often introduces large amounts of bias. Although many techniques have been developed for imputing missing data, the image imputation is still difficult due to complicated nature of natural images. To address this problem, here we proposed a novel framework for missing image data imputation, called Collaborative Generative Adversarial Network (CollaGAN). CollaGAN converts an image imputation problem to a multi-domain images-to-image translation task so that a single generator and discriminator network can successfully estimate the missing data using the remaining clean data set. We demonstrate that CollaGAN produces the images with a higher visual quality compared to the existing competing approaches in various image imputation tasks.