CollaGAN : Collaborative GAN for Missing Image Data Imputation
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation2018
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network2017
- Synthetic MRI for Clinical Neuroimaging: Results of the Magnetic Resonance Image Compilation (MAGiC) Prospective, Multicenter, Multireader TrialAmerican Journal of Neuroradiology, 2017
- Presentation and validation of the Radboud Faces DatabaseCognition and Emotion, 2010
- An introduction to modern missing data analysesJournal of School Psychology, 2010
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004