Latent Filter Scaling for Multimodal Unsupervised Image-to-Image Translation
| Autor: | Neil Smith, Peter Wonka, Yazeed Alharbi |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
FOS: Computer and information sciences
business.industry Computer science Deep learning Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Pattern recognition 02 engineering and technology Filter (signal processing) 010501 environmental sciences Translation (geometry) 01 natural sciences Domain (software engineering) Image (mathematics) 0202 electrical engineering electronic engineering information engineering Benchmark (computing) Code (cryptography) Image translation 020201 artificial intelligence & image processing Artificial intelligence business 0105 earth and related environmental sciences |
| Zdroj: | CVPR |
| DOI: | 10.48550/arxiv.1812.09877 |
| Popis: | In multimodal unsupervised image-to-image translation tasks, the goal is to translate an image from the source domain to many images in the target domain. We present a simple method that produces higher quality images than current state-of-the-art while maintaining the same amount of multimodal diversity. Previous methods follow the unconditional approach of trying to map the latent code directly to a full-size image. This leads to complicated network architectures with several introduced hyperparameters to tune. By treating the latent code as a modifier of the convolutional filters, we produce multimodal output while maintaining the traditional Generative Adversarial Network (GAN) loss and without additional hyperparameters. The only tuning required by our method controls the tradeoff between variability and quality of generated images. Furthermore, we achieve disentanglement between source domain content and target domain style for free as a by-product of our formulation. We perform qualitative and quantitative experiments showing the advantages of our method compared with the state-of-the art on multiple benchmark image-to-image translation datasets. Comment: Accepted to CVPR2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|