Attribute-Driven Spontaneous Motion in Unpaired Image Translation
arXiv:1907.01452
Abstract
Current image translation methods, albeit effective to produce high-quality results in various applications, still do not consider much geometric transform. We in this paper propose the spontaneous motion estimation module, along with a refinement part, to learn attribute-driven deformation between source and target domains. Extensive experiments and visualization demonstrate effectiveness of these modules. We achieve promising results in unpaired-image translation tasks, and enable interesting applications based on spontaneous motion.
arXiv commentAccepted by ICCV 2019
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Unsupervised Cross-Domain Image Generation
- Multimodal Unsupervised Image-to-Image Translation
- DRIT++: Diverse Image-to-Image Translation via Disentangled Representations
- CariGANs: Unpaired Photo-to-Caricature Translation
- Semantic Facial Expression Editing using Autoencoded Flow
- SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
- Image to Image Translation for Domain Adaptation