Synthetic Image Augmentation for Damage Region Segmentation using Conditional GAN with Structure Edge

no code implementations • 7 May 2020 • Takato Yasuno, Michihiro Nakajima, Tomoharu Sekiguchi, Kazuhiro Noda, Kiyoshi Aoyanagi, Sakura Kato

We propose a synthetic augmentation procedure to generate damaged images using the image-to-image translation mapping from the tri-categorical label that consists the both semantic label and structure edge to the real damage image.

Image Augmentation Image-to-Image Translation