V-LinkNet: Learning Contextual Inpainting Across Latent Space of Generative Adversarial Network. (arXiv:2201.00323v1 [cs.CV])

Deep learning methods outperform traditional methods in image inpainting. In
order to generate contextual textures, researchers are still working to improve
on existing methods and propose models that can extract, propagate, and
reconstruct features similar to ground-truth regions. Furthermore, the lack of
a high-quality feature transfer mechanism in deeper layers contributes to
persistent aberrations on generated inpainted regions. To address these
limitations, we propose the V-LinkNet cross-space learning strategy network. To
improve learning on contextualised features, we design a loss …

arxiv cv generative adversarial network learning space