{"id":429,"date":"2016-11-25T11:27:33","date_gmt":"2016-11-25T11:27:33","guid":{"rendered":"http:\/\/liipetti.net\/erratic\/?p=429"},"modified":"2018-05-07T11:44:56","modified_gmt":"2018-05-07T11:44:56","slug":"imaginary-landscapes-using-pix2pix","status":"publish","type":"post","link":"http:\/\/liipetti.net\/erratic\/2016\/11\/25\/imaginary-landscapes-using-pix2pix\/","title":{"rendered":"Imaginary landscapes using pix2pix"},"content":{"rendered":"

Pix2pix<\/a> is a brand-new tool which is intended to allow application-independent training of any kind of image transform. All that is needed is a dataset containing image pairs, A and B, and one can train a network to transform to either direction. Possible applications include colorization, segmentation, line drawing to image, map to satellite view, stylization and so on. The operations work in both directions, so with a properly trained network one can generate a plausible satellite view from a map, or a building facade from a colored segmentation. Check the link above or\u00a0the paper on the method<\/a> for more information.<\/p>\n

\"2\"<\/a> \"2\"<\/a><\/p>\n

I made a first quick test using Graz02<\/a> dataset, consisting of city views with people and corresponding images with human silhouttes on white background, and then had a look how Pix2pix will construct a full view from a mere silhouette. The dataset was very small, so I did certainly not believe spectacular performance. I was just looking for something interesting. Understandably, the model did not perform well on a silhoutte which was not part of the training set. It produced a human shape with a background which did not change much when run with different input images.<\/p>\n

But the results obtained using silhouttes from the training set were quite interesting, from an artistic point of view.<\/p>\n