DAM-GAN : Image Inpainting using Dynamic Attention Map based on Fake Texture Detection
This work addresses a specific issue in image inpainting for computer vision applications, representing an incremental improvement over existing GAN-based methods.
The paper tackles the problem of fake textures causing pixel artifacts and color inconsistency in GAN-based image inpainting by proposing DAM-GAN, which uses dynamic attention maps to detect and reduce these inconsistencies, achieving superior results on CelebA-HQ and Places2 datasets compared to other approaches.
Deep neural advancements have recently brought remarkable image synthesis performance to the field of image inpainting. The adaptation of generative adversarial networks (GAN) in particular has accelerated significant progress in high-quality image reconstruction. However, although many notable GAN-based networks have been proposed for image inpainting, still pixel artifacts or color inconsistency occur in synthesized images during the generation process, which are usually called fake textures. To reduce pixel inconsistency disorder resulted from fake textures, we introduce a GAN-based model using dynamic attention map (DAM-GAN). Our proposed DAM-GAN concentrates on detecting fake texture and products dynamic attention maps to diminish pixel inconsistency from the feature maps in the generator. Evaluation results on CelebA-HQ and Places2 datasets with other image inpainting approaches show the superiority of our network.