# Semantic Image Synthesis with Semantically Coupled VQ-Model

arXiv: https://arxiv.org/abs/2209.02536 · HTML: https://mlsanity.com/paper/2209.02536/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 6 Sep 2022.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Hierarchical Quantized Autoencoders](https://mlsanity.com/paper/2002.08111/) (2020)
- [SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects](https://mlsanity.com/paper/2004.04977/) (2020)
- [Learning Hierarchical Semantic Image Manipulation through Structured Representations](https://mlsanity.com/paper/1808.07535/) (2018)

## Built on by (most cited first, 4 of 4)

- [Freestyle Layout-to-Image Synthesis](https://mlsanity.com/paper/2303.14412/) (2023)
- [If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection](https://mlsanity.com/paper/2305.13308/) (2023)
- [Enhancing Object Coherence in Layout-to-Image Synthesis](https://mlsanity.com/paper/2311.10522/) (2023)
- [Distillation of a tractable model from the VQ-VAE](https://mlsanity.com/paper/2509.01400/) (2025)

## Abstract (arXiv)

Semantic image synthesis enables control over unconditional image generation by allowing guidance on what is being generated. We conditionally synthesize the latent space from a vector quantized model (VQ-model) pre-trained to autoencode images. Instead of training an autoregressive Transformer on separately learned conditioning latents and image latents, we find that jointly learning the conditioning and image latents significantly improves the modeling capabilities of the Transformer model. While our jointly trained VQ-model achieves a similar reconstruction performance to a vanilla VQ-model for both semantic and image latents, tying the two modalities at the autoencoding stage proves to be an important ingredient to improve autoregressive modeling performance. We show that our model improves semantic image synthesis using autoregressive models on popular semantic image datasets ADE20k, Cityscapes and COCO-Stuff.