Multi-Modality Image Inpainting using Generative Adversarial Networks
This addresses a gap in computer vision for applications requiring both image restoration and style transfer, but it appears incremental as it builds on existing GAN-based methods.
The paper tackles the problem of combining image inpainting with multi-modality image-to-image translation, proposing a model that achieves promising qualitative and quantitative results in tasks like night-to-day translation and inpainting.
Deep learning techniques, especially Generative Adversarial Networks (GANs) have significantly improved image inpainting and image-to-image translation tasks over the past few years. To the best of our knowledge, the problem of combining the image inpainting task with the multi-modality image-to-image translation remains intact. In this paper, we propose a model to address this problem. The model will be evaluated on combined night-to-day image translation and inpainting, along with promising qualitative and quantitative results.