TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation
arXiv:1904.09571
Abstract
Unsupervised image-to-image translation aims at learning a mapping between two visual domains. However, learning a translation across large geometry variations always ends up with failure. In this work, we present a novel disentangle-and-translate framework to tackle the complex objects image-to-image translation task. Instead of learning the mapping on the image space directly, we disentangle image space into a Cartesian product of the appearance and the geometry latent spaces. Specifically, we first introduce a geometry prior loss and a conditional VAE loss to encourage the network to learn independent but complementary representations. The translation is then built on appearance and geometry space separately. Extensive experiments demonstrate the superior performance of our method to other state-of-the-art approaches, especially in the challenging near-rigid and non-rigid objects translation tasks. In addition, by taking different exemplars as the appearance references, our method also supports multimodal translation. Project page: https://wywu.github.io/projects/TGaGa/TGaGa.html
arXiv commentAccepted to CVPR 2019. Project page: https://wywu.github.io/projects/TGaGa/TGaGa.html
References in corpus (13)
- Auto-Encoding Variational Bayes
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
- Toward Multimodal Image-to-Image Translation
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
- CariGANs: Unpaired Photo-to-Caricature Translation
- Multi-Context Attention for Human Pose Estimation
- Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation
- Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning
- Conditional Image-to-Image Translation
- ReenactGAN: Learning to Reenact Faces via Boundary Transfer
- Every Smile is Unique: Landmark-Guided Diverse Smile Generation