Track description

Given an image with multiple blocks of black pixels occluding the original image, and a mask indicating the position and size of these blocks, we want to be able to restore the masked parts of the image in a way that resembles the original content and looks plausible to a human. In order to evaluate the recovery of the missing parts, we will evaluate common used metrics as well as a human pose estimation score,  in occluded images without mask. We can see an example of this on the following image:


WCCI'18 Inpainting Challenge

Codalab is public for all three tracks.

Track 1

Track 2

Track 3