SimilarityGAN: Using Similarity to Loosen Structural Constraints in Generative Adversarial Models
Document Type
Conference Proceeding
Publication Date
1-1-2021
Abstract
Recently, generative adversarial networks have performed extremely well in image translation. When translating images current models adhere to a strict structural symmetry between the input and output images. This paper, presents a technique for image translation involving a pair of image domains that allows the output image to go beyond the structural symmetry constraints imposed by the input. By using a siamese model as the discriminator, we condition the generator to produce images that are only similar, rather than identical to the input. We show experimentally that using this modified loss a generator can generate realistic images for complex problems that only loosely adhere to the structure of the input.
Publication Source (Journal or Book title)
Dicta 2021 2021 International Conference on Digital Image Computing Techniques and Applications
Recommended Citation
Collier, E., & Mukhopadhyay, S. (2021). SimilarityGAN: Using Similarity to Loosen Structural Constraints in Generative Adversarial Models. Dicta 2021 2021 International Conference on Digital Image Computing Techniques and Applications https://doi.org/10.1109/DICTA52665.2021.9647086