Evangelos Ntavelis

TL;DR: SESAME, a novel generator-discriminator pair for Semantic Editing of Scenes by Adding, Manipulating or Erasing objects, is proposed, composed of two input streams that independently process the image and its semantics, using the latter to manipulate the results of the former.

TL;DR: This paper reviews the AIM 2020 challenge on extreme image inpainting and proposes solutions and results for two different tracks: classical image inPainting and semantically guided image in Painting.

TL;DR: SESAME as discussed by the authors is a generator-discriminator pair for semantic image editing of scenes by adding, manipulating or erasing objects, where the user provides the semantic labels of the areas to be edited and the generator synthesizes the corresponding pixels.

TL;DR: The AIM 2020 Extreme Image Inpainting Challenge as mentioned in this paper focused on semi-guided and classical image inpainting, and the goal was to inpaint large parts of the image with no supervision.

TL;DR: This work proposes the design of scale-consistent positional encodings invariant to the generator's layers transformations that enables the generation of arbitrary-scale images even at scales unseen during training.