Corpus ID: 220280381

Swapping Autoencoder for Deep Image Manipulation

@article{Park2020SwappingAF,
  title={Swapping Autoencoder for Deep Image Manipulation},
  author={Taesung Park and Jun-Yan Zhu and O. Wang and Jingwan Lu and E. Shechtman and Alexei A. Efros and Richard Zhang},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.00653}
}
Deep generative models have become increasingly effective at producing realistic images from randomly sampled seeds, but using such models for controllable manipulation of existing images remains challenging. We propose the Swapping Autoencoder, a deep model designed specifically for image manipulation, rather than random sampling. The key idea is to encode an image with two independent components and enforce that any swapped combination maps to a realistic image. In particular, we encourage… Expand
SMILE: Semantically-guided Multi-attribute Image and Layout Editing
Online Exemplar Fine-Tuning for Image-to-Image Translation
Dual In-painting Model for Unsupervised Gaze Correction and Animation in the Wild
V2V: A Deep Learning Approach to Variable-to-Variable Selection and Translation for Multivariate Time-Varying Data
DeepFaceEditing: Deep Face Generation and Editing with Disentangled Geometry and Appearance Control
Image-to-Image Translation: Methods and Applications
A Latent Transformer for Disentangled and Identity-Preserving Face Editing
ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity
...
1
2
3
4
...

References

SHOWING 1-10 OF 102 REFERENCES
SinGAN: Learning a Generative Model From a Single Natural Image
Large Scale GAN Training for High Fidelity Natural Image Synthesis
Generative Visual Manipulation on the Natural Image Manifold
Scribbler: Controlling Deep Image Synthesis with Sketch and Color
InGAN: Capturing and Retargeting the “DNA” of a Natural Image
InGAN: Capturing and Remapping the "DNA" of a Natural Image
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
Invertible Conditional GANs for image editing
Analyzing and Improving the Image Quality of StyleGAN
TextureGAN: Controlling Deep Image Synthesis with Texture Patches
...
1
2
3
4
5
...