# Generative Image Modeling Using Spatial LSTMs

arXiv: https://arxiv.org/abs/1506.03478 · HTML: https://mlsanity.com/paper/1506.03478/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2015.

## Built on by (most cited first, 30 of 35)

- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models](https://mlsanity.com/paper/2103.04922/) (2021)
- [An Introduction to Neural Data Compression](https://mlsanity.com/paper/2202.06533/) (2022)
- [Residual Mixture of Experts](https://mlsanity.com/paper/2204.09636/) (2022)
- [MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance](https://mlsanity.com/paper/2505.03804/) (2025)
- [Regression as Classification: Influence of Task Formulation on Neural Network Features](https://mlsanity.com/paper/2211.05641/) (2022)
- [Diagnosing and Fixing Manifold Overfitting in Deep Generative Models](https://mlsanity.com/paper/2204.07172/) (2022)
- [Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Model](https://mlsanity.com/paper/2303.06519/) (2023)
- [Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics](https://mlsanity.com/paper/2105.08164/) (2021)
- [Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms](https://mlsanity.com/paper/1802.07417/) (2018)
- [Mixture of Lookup Experts](https://mlsanity.com/paper/2503.15798/) (2025)
- [Training-efficient density quantum machine learning](https://mlsanity.com/paper/2405.20237/) (2024)
- [Lossless Coding of Point Cloud Geometry using a Deep Generative Model](https://mlsanity.com/paper/2107.00400/) (2021)
- [MoLAE: Mixture of Latent Experts for Parameter-Efficient Language Models](https://mlsanity.com/paper/2503.23100/) (2025)
- [Neural Experts: Mixture of Experts for Implicit Neural Representations](https://mlsanity.com/paper/2410.21643/) (2024)
- [SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecasting](https://mlsanity.com/paper/2312.14880/) (2023)
- [Designing Large Foundation Models for Efficient Training and Inference: A Survey](https://mlsanity.com/paper/2409.01990/) (2024)
- [Denoising Deep Generative Models](https://mlsanity.com/paper/2212.01265/) (2022)
- [Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling](https://mlsanity.com/paper/2103.08877/) (2021)
- [No Need to Talk: Asynchronous Mixture of Language Models](https://mlsanity.com/paper/2410.03529/) (2024)
- [Short term prediction of demand for ride hailing services: A deep learning approach](https://mlsanity.com/paper/2212.03956/) (2022)
- [SPRINT: Robust Model Attribution of Generated Images via Secret Pixel Reconstruction](https://mlsanity.com/paper/2508.05691/) (2025)
- [CAGAN: Text-To-Image Generation with Combined Attention GANs](https://mlsanity.com/paper/2104.12663/) (2021)
- [Neural Inverse Transform Sampler](https://mlsanity.com/paper/2206.11172/) (2022)
- [An Introduction to the Practical and Theoretical Aspects of Mixture-of-Experts Modeling](https://mlsanity.com/paper/1707.03538/) (2017)
- [PixelPyramids: Exact Inference Models from Lossless Image Pyramids](https://mlsanity.com/paper/2110.08787/) (2021)
- [Compression of GPS Trajectories using Autoencoders](https://mlsanity.com/paper/2301.07420/) (2023)
- [Adversarial Likelihood Estimation With One-Way Flows](https://mlsanity.com/paper/2307.09882/) (2023)
- [Self-Supervised Learning Based Handwriting Verification](https://mlsanity.com/paper/2405.18320/) (2024)
- [Poly-Autoregressive Prediction for Modeling Interactions](https://mlsanity.com/paper/2502.08646/) (2025)

## Abstract (arXiv)

Modeling the distribution of natural images is challenging, partly because of strong statistical dependencies which can extend over hundreds of pixels. Recurrent neural networks have been successful in capturing long-range dependencies in a number of problems but only recently have found their way into generative image models. We here introduce a recurrent image model based on multi-dimensional long short-term memory units which are particularly suited for image modeling due to their spatial structure. Our model scales to images of arbitrary size and its likelihood is computationally tractable. We find that it outperforms the state of the art in quantitative comparisons on several image datasets and produces promising results when used for texture synthesis and inpainting.