# DRAW: A Recurrent Neural Network For Image Generation

arXiv: https://arxiv.org/abs/1502.04623 · HTML: https://mlsanity.com/paper/1502.04623/

## Key facts

- Cited by 191 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Feb 2015.

## Built on by (most cited first, 30 of 191)

- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors](https://mlsanity.com/paper/2203.13131/) (2022)
- [Human Preference Score: Better Aligning Text-to-Image Models with Human Preference](https://mlsanity.com/paper/2303.14420/) (2023)
- [Cross-Modal Contrastive Learning for Text-to-Image Generation](https://mlsanity.com/paper/2101.04702/) (2021)
- [Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models](https://mlsanity.com/paper/2103.04922/) (2021)
- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [JourneyDB: A Benchmark for Generative Image Understanding](https://mlsanity.com/paper/2307.00716/) (2023)
- [Scalable Adaptive Computation for Iterative Generation](https://mlsanity.com/paper/2212.11972/) (2022)
- [Fast Convergence of DETR with Spatially Modulated Co-Attention](https://mlsanity.com/paper/2101.07448/) (2021)
- [Paint by Word](https://mlsanity.com/paper/2103.10951/) (2021)
- [Generalization and Robustness Implications in Object-Centric Learning](https://mlsanity.com/paper/2107.00637/) (2021)
- [Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis](https://mlsanity.com/paper/2208.13753/) (2022)
- [Learning to Compose Visual Relations](https://mlsanity.com/paper/2111.09297/) (2021)
- [Synthetic Data -- what, why and how?](https://mlsanity.com/paper/2205.03257/) (2022)
- [PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement](https://mlsanity.com/paper/2403.04014/) (2024)
- [Improving Object-centric Learning with Query Optimization](https://mlsanity.com/paper/2210.08990/) (2022)
- [SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing](https://mlsanity.com/paper/2112.02236/) (2021)
- [Any-Resolution AI-Generated Image Detection by Spectral Learning](https://mlsanity.com/paper/2411.19417/) (2024)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Consistency Regularization for Variational Auto-Encoders](https://mlsanity.com/paper/2105.14859/) (2021)
- [TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis](https://mlsanity.com/paper/2307.15042/) (2023)
- [Generating Synthetic Mixed-type Longitudinal Electronic Health Records for Artificial Intelligent Applications](https://mlsanity.com/paper/2112.12047/) (2021)
- [DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis](https://mlsanity.com/paper/2108.12141/) (2021)
- [Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts](https://mlsanity.com/paper/2109.08857/) (2021)
- [Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI](https://mlsanity.com/paper/2111.06061/) (2021)
- [Recent Advances for Quantum Neural Networks in Generative Learning](https://mlsanity.com/paper/2206.03066/) (2022)
- [Few-Shot Diffusion Models](https://mlsanity.com/paper/2205.15463/) (2022)
- [Content and Style Aware Generation of Text-line Images for Handwriting Recognition](https://mlsanity.com/paper/2204.05539/) (2022)
- [Multimodal Dialogue Response Generation](https://mlsanity.com/paper/2110.08515/) (2021)

## Abstract (arXiv)

This paper introduces the Deep Recurrent Attentive Writer (DRAW) neural network architecture for image generation. DRAW networks combine a novel spatial attention mechanism that mimics the foveation of the human eye, with a sequential variational auto-encoding framework that allows for the iterative construction of complex images. The system substantially improves on the state of the art for generative models on MNIST, and, when trained on the Street View House Numbers dataset, it generates images that cannot be distinguished from real data with the naked eye.