# SATURN: Autoregressive Image Generation Guided by Scene Graphs

arXiv: https://arxiv.org/abs/2508.14502 · HTML: https://mlsanity.com/paper/2508.14502/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 26 references that are in the map.
- First posted on arXiv 20 Aug 2025.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [Scaling up GANs for Text-to-Image Synthesis](https://mlsanity.com/paper/2303.05511/) (2023)
- [Image Generation from Scene Graphs](https://mlsanity.com/paper/1804.01622/) (2018)
- [VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance](https://mlsanity.com/paper/2204.08583/) (2022)
- [Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training](https://mlsanity.com/paper/2211.11138/) (2022)
- [EGTR: Extracting Graph from Transformer for Scene Graph Generation](https://mlsanity.com/paper/2404.02072/) (2024)
- [VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling](https://mlsanity.com/paper/2408.01181/) (2024)
- [In Defense of Scene Graphs for Image Captioning](https://mlsanity.com/paper/2102.04990/) (2021)
- [Image-to-Image Retrieval by Learning Similarity between Scene Graphs](https://mlsanity.com/paper/2012.14700/) (2020)
- [Visual-Relation Conscious Image Generation from Structured-Text](https://mlsanity.com/paper/1908.01741/) (2019)

## Built on by (most cited first, 3 of 3)

- [VENUS: Visual Editing with Noise Inversion Using Scene Graphs](https://mlsanity.com/paper/2601.07219/) (2026)
- [SimGraph: A Unified Framework for Scene Graph-Based Image Generation and Editing](https://mlsanity.com/paper/2601.21498/) (2026)
- [Dependency-Aware Discrete Diffusion for Scene Graph Generation](https://mlsanity.com/paper/2605.09065/) (2026)

## Abstract (arXiv)

State-of-the-art text-to-image models excel at photorealistic rendering but often struggle to capture the layout and object relationships implied by complex prompts. Scene graphs provide a natural structural prior, yet previous graph-guided approaches have typically relied on heavy GAN or diffusion pipelines, which lag behind modern autoregressive architectures in both speed and fidelity. We introduce SATURN (Structured Arrangement of Triplets for Unified Rendering Networks), a lightweight extension to VAR-CLIP that translates a scene graph into a salience-ordered token sequence, enabling a frozen CLIP-VQ-VAE backbone to interpret graph structure while fine-tuning only the VAR transformer. On the Visual Genome dataset, SATURN reduces FID from 56.45% to 21.62% and increases the Inception Score from 16.03 to 24.78, outperforming prior methods such as SG2IM and SGDiff without requiring extra modules or multi-stage training. Qualitative results further confirm improvements in object count fidelity and spatial relation accuracy, showing that SATURN effectively combines structural awareness with state-of-the-art autoregressive fidelity.