Learning image-to-image translation using paired and unpaired training samples
Explore this paper's citation graph
Summary
This work proposes a new general purpose image-to-image translation model that is able to utilize both paired and unpaired training data simultaneously, and is the first work to consider such hybrid setup in image- to- image translation.
- Type
- preprint
- Published
- 2018-05-08
- Cited by
- 46
- References
- 40
- Access
- Open access
- OpenAlex
- https://openalex.org/W2801901913
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:13680524
Keywords
Image translation, Image (mathematics), Translation (biology), Computer science, Artificial intelligence
References
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Fully convolutional networks for semantic segmentation
- Data-driven hallucination of different times of day from a single outdoor photo
- Conditional Generative Adversarial Nets
- Attribute2Image: Conditional Image Generation from Visual Attributes
- Deep Residual Learning for Image Recognition
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Context Encoders: Feature Learning by Inpainting
- Tutorial on Variational Autoencoders
- Coupled Generative Adversarial Networks
- Image-to-Image Translation with Conditional Adversarial Networks
- Multi-class Generative Adversarial Networks with the L2 Loss Function
- Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
- Scribbler: Controlling Deep Image Synthesis with Sketch and Color
- StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
- Learning from Simulated and Unsupervised Images through Adversarial Training
- Mastering Sketching
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks
- DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
- Real-time user-guided image colorization with learned deep priors
Cited by
- ICface: Interpretable and Controllable Face Reenactment Using GANs
- Implicit Pairs for Boosting Unpaired Image-to-Image Translation
- The Point Where Reality Meets Fantasy: Mixed Adversarial Generators for Image Splice Detection
- Extremely Weak Supervised Image-to-Image Translation for Semantic Segmentation
- Noise Adaptation Generative Adversarial Network for Medical Image Analysis
- Low Light Video Enhancement Using Synthetic Data Produced with an Intermediate Domain Mapping
- Deep Generative Adversarial Networks for Image-to-Image Translation: A Review
- Увеличение робастности нейронных сетей за счет генерации векторных представлений, инвариантных к атрибутам
- Assessing autonomous ship navigation using bridge simulators enhanced by cycle-consistent adversarial networks
- Görüntüden Görüntüye Dönüşüm ve Görüntü Sentezleme Yapan Üretici Çekişmeli Ağların İncelenmesi
- RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations
- Paired-unpaired Unsupervised Attention Guided GAN with transfer learning for bidirectional brain MR-CT synthesis
- Generating Virtual Short Tau Inversion Recovery (STIR) Images from T1- and T2-Weighted Images Using a Conditional Generative Adversarial Network in Spine Imaging
- MV-TON: Memory-based Video Virtual Try-on network
- Improvement of megavoltage computed tomography image quality for adaptive helical tomotherapy using cycleGAN‐based image synthesis with small datasets
- Crack Image Synthesis and Segmentation using Paired Image Translation
- Structure Unbiased Adversarial Model for Medical Image Segmentation
- Path Generator with Unpaired Samples Employing Generative Adversarial Networks
- Rendering the image of glare effect based on paired and unpaired dual generative adversarial network
- AptSim2Real: Approximately-Paired Sim-to-Real Image Translation