CollaGAN: Collaborative GAN for Missing Image Data Imputation
Authors:
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2482-2491
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 convert the 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 19 references indexed in Scilit:
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture2015
- Going deeper with convolutions2015
- Presentation and validation of the Radboud Faces DatabaseCognition and Emotion, 2010
- Imaging Modalities in Brain Tumors2010
- Multi-PIEImage and Vision Computing, 2010
- An introduction to modern missing data analysesJournal of School Psychology, 2010
- Sketch2PhotoACM Transactions on Graphics, 2009
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Image quilting for texture synthesis and transfer2001