Content and Colour Distillation for Learning Image Translations with the Spatial Profile Loss
arXiv:1908.00274
Abstract
Generative adversarial networks has emerged as a defacto standard for image translation problems. To successfully drive such models, one has to rely on additional networks e.g., discriminators and/or perceptual networks. Training these networks with pixel based losses alone are generally not sufficient to learn the target distribution. In this paper, we propose a novel method of computing the loss directly between the source and target images that enable proper distillation of shape/content and colour/style. We show that this is useful in typical image-to-image translations allowing us to successfully drive the generator without relying on additional networks. We demonstrate this on many difficult image translation problems such as image-to-image domain mapping, single image super-resolution and photo realistic makeup transfer. Our extensive evaluation shows the effectiveness of the proposed formulation and its ability to synthesize realistic images. [Code release: https://github.com/ssarfraz/SPL]
arXiv commentBMVC 2019
References in corpus (10)
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
- Toward Multimodal Image-to-Image Translation
- Which Training Methods for GANs do actually Converge?
- Perceptual Adversarial Networks for Image-to-Image Transformation
- A new face database simultaneously acquired in visible, near infrared and thermal spectrum
- Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
- Makeup like a superstar: Deep Localized Makeup Transfer Network
- Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation
- Anti-Makeup: Learning A Bi-Level Adversarial Network for Makeup-Invariant Face Verification