Learning What and Where to Draw
Explore this paper's citation graph
Summary
This work proposes a new model, the Generative Adversarial What-Where Network (GAWWN), that synthesizes images given instructions describing what content to draw in which location, and shows high-quality 128 x 128 image synthesis on the Caltech-UCSD Birds dataset.
- Type
- article
- Published
- 2016-10-08
- Cited by
- 644
- References
- 27
- Access
- Open access
- OpenAlex
- https://openalex.org/W2530372461
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:1515901
Keywords
Computer science, Object (grammar), Bounding overwatch, Adversarial system, Minimum bounding box
References
- Deep Boltzmann Machines
- Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models
- Deep Convolutional Inverse Graphics Network
- The Caltech-UCSD Birds-200-2011 Dataset
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Learning to generate chairs with convolutional neural networks
- Auto-Encoding Variational Bayes
- Evaluation of output embeddings for fine-grained image classification
- 2D Human Pose Estimation: New Benchmark and State of the Art Analysis
- Action-Conditional Video Prediction using Deep Networks in Atari Games
- The Neural Autoregressive Distribution Estimator
- On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
- Deep Visual Analogy-Making
- Pixel Recurrent Neural Networks
- One-Shot Generalization in Deep Generative Models
- Learning Deep Representations of Fine-Grained Visual Descriptions
- Generative Adversarial Text to Image Synthesis
- Spatial Transformer Networks
- Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
Cited by
- Image-to-Image Translation with Conditional Adversarial Networks
- Invertible Conditional GANs for image editing
- Unrolled Generative Adversarial Networks
- CDVAE: Co-embedding Deep Variational Auto Encoder for Conditional Variational Generation
- 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 Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
- Attentive Explanations: Justifying Decisions and Pointing to the Evidence
- TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
- I2T2I: Learning text to image synthesis with textual data augmentation
- Semi-Latent GAN: Learning to generate and modify facial images from attributes
- An Overview of Cross-Media Retrieval: Concepts, Methodologies, Benchmarks, and Challenges
- Learning to Generate Long-term Future via Hierarchical Prediction
- The Pose Knows: Video Forecasting by Generating Pose Futures
- Pose Guided Person Image Generation
- DeLiGAN: Generative Adversarial Networks for Diverse and Limited Data
- Latent Variable PixelCNNs for Natural Image Modeling
- Adjusting transient attributes of outdoor images using generative adversarial networks
- Neuroscience-Inspired Artificial Intelligence.