Multi-Modality Image Inpainting Using Generative Adversarial Networks
Authors:
- 24 July 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1909-1916
Abstract
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.Keywords
Funding Information
- Natural Sciences and Engineering Research Council of Canada (NSERC)
This publication has 13 references indexed in Scilit:
- Rethinking the Truly Unsupervised Image-to-Image Translation2021
- Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation2021
- Research on image Inpainting algorithm of improved GAN based on two-discriminations networksApplied Intelligence, 2020
- Contrastive Learning for Unpaired Image-to-Image Translation2020
- Recurrent Feature Reasoning for Image Inpainting2020
- UCTGAN: Diverse Image Inpainting Based on Unsupervised Cross-Space Translation2020
- Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting2020
- Learning Oracle Attention for High-Fidelity Face Completion2020
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Image-to-Image Translation with Conditional Adversarial Networks2017