Conference Proceedings

Boosted GAN with Semantically Interpretable Information for Image Inpainting

A Li, J Qi, R Zhang, R Kotagiri

2019 International Joint Conference on Neural Networks (IJCNN) | IEEE | Published : 2019


Image inpainting aims at restoring missing regions of corrupted images, which has many applications such as image restoration and object removal. However, current GAN-based inpainting models fail to explicitly consider the semantic consistency between restored images and original images. For example, given a male image with image region of one eye missing, current models may restore it with a female eye. This is due to the ambiguity of GAN-based inpainting models: these models can generate many possible restorations given a missing region. To address this limitation, our key insight is that semantically interpretable information (such as attribute and segmentation information) of input image..

View full abstract