# EdiBERT, a generative model for image editing

arXiv: https://arxiv.org/abs/2111.15264 · HTML: https://mlsanity.com/paper/2111.15264/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 57 references that are in the map.
- First posted on arXiv 30 Nov 2021.

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions](https://mlsanity.com/paper/2102.05379/) (2021)
- [Designing an Encoder for StyleGAN Image Manipulation](https://mlsanity.com/paper/2102.02766/) (2021)
- [Reliable Fidelity and Diversity Metrics for Generative Models](https://mlsanity.com/paper/2002.09797/) (2020)

## Built on by (most cited first, 13 of 13)

- [DiffEdit: Diffusion-based semantic image editing with mask guidance](https://mlsanity.com/paper/2210.11427/) (2022)
- [StyleGAN knows Normal, Depth, Albedo, and More](https://mlsanity.com/paper/2306.00987/) (2023)
- [Deep Equilibrium Approaches to Diffusion Models](https://mlsanity.com/paper/2210.12867/) (2022)
- [COFS: Controllable Furniture layout Synthesis](https://mlsanity.com/paper/2205.14657/) (2022)
- [FashionTex: Controllable Virtual Try-on with Text and Texture](https://mlsanity.com/paper/2305.04451/) (2023)
- [End-to-End Visual Editing with a Generatively Pre-Trained Artist](https://mlsanity.com/paper/2205.01668/) (2022)
- [Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddings](https://mlsanity.com/paper/2509.22925/) (2025)
- [DiffGAR: Model-Agnostic Restoration from Generative Artifacts Using Image-to-Image Diffusion Models](https://mlsanity.com/paper/2210.08573/) (2022)
- [Controllable Image Generation via Collage Representations](https://mlsanity.com/paper/2304.13722/) (2023)
- [Dimathtt[M]O: Distilling Masked Diffusion Models into One-step Generator](https://mlsanity.com/paper/2503.15457/) (2025)
- [Rapid Review of Generative AI in Smart Medical Applications](https://mlsanity.com/paper/2406.06627/) (2024)
- [Multidimensional Byte Pair Encoding: Shortened Sequences for Improved Visual Data Generation](https://mlsanity.com/paper/2411.10281/) (2024)
- [Thermal-Infrared Remote Target Detection System for Maritime Rescue based on Data Augmentation with 3D Synthetic Data](https://mlsanity.com/paper/2310.20412/) (2023)

## Abstract (arXiv)

Advances in computer vision are pushing the limits of im-age manipulation, with generative models sampling detailed images on various tasks. However, a specialized model is often developed and trained for each specific task, even though many image edition tasks share similarities. In denoising, inpainting, or image compositing, one always aims at generating a realistic image from a low-quality one. In this paper, we aim at making a step towards a unified approach for image editing. To do so, we propose EdiBERT, a bi-directional transformer trained in the discrete latent space built by a vector-quantized auto-encoder. We argue that such a bidirectional model is suited for image manipulation since any patch can be re-sampled conditionally to the whole image. Using this unique and straightforward training objective, we show that the resulting model matches state-of-the-art performances on a wide variety of tasks: image denoising, image completion, and image composition.