Search Results for author: Jookyung Song

Found 1 papers, 0 papers with code

Semantics-Guided Object Removal for Facial Images: with Broad Applicability and Robust Style Preservation

no code implementations29 Sep 2022 Jookyung Song, Yeonjin Chang, SeongUk Park, Nojun Kwak

U-net, a conventional approach for conditional GANs, retains fine details of unmasked regions but the style of the reconstructed image is inconsistent with the rest of the original image and only works robustly when the size of the occluding object is small enough.

Image Inpainting

Cannot find the paper you are looking for? You can Submit a new open access paper.