# DualVAE: Controlling Colours of Generated and Real Images

arXiv: https://arxiv.org/abs/2305.18769 · HTML: https://mlsanity.com/paper/2305.18769/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 56 references that are in the map.
- First posted on arXiv 30 May 2023.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Assessing Generative Models via Precision and Recall](https://mlsanity.com/paper/1806.00035/) (2018)
- [Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature](https://mlsanity.com/paper/1505.00855/) (2015)
- [Deep Photo Style Transfer](https://mlsanity.com/paper/1703.07511/) (2017)
- [A Variational U-Net for Conditional Appearance and Shape Generation](https://mlsanity.com/paper/1804.04694/) (2018)
- [ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis](https://mlsanity.com/paper/2108.08827/) (2021)
- [Colorization Transformer](https://mlsanity.com/paper/2102.04432/) (2021)
- [Disentangling factors of variation in deep representations using adversarial training](https://mlsanity.com/paper/1611.03383/) (2016)
- [Variational Autoencoders Pursue PCA Directions (by Accident)](https://mlsanity.com/paper/1812.06775/) (2018)
- [Instance-aware Image Colorization](https://mlsanity.com/paper/2005.10825/) (2020)
- [Unsupervised Discovery of Object Landmarks as Structural Representations](https://mlsanity.com/paper/1804.04412/) (2018)
- [SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows](https://mlsanity.com/paper/2007.02731/) (2020)
- [Aligning Latent and Image Spaces to Connect the Unconnectable](https://mlsanity.com/paper/2104.06954/) (2021)
- [HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms](https://mlsanity.com/paper/2011.11731/) (2020)
- [ChromaGAN: Adversarial Picture Colorization with Semantic Class Distribution](https://mlsanity.com/paper/1907.09837/) (2019)

## Abstract (arXiv)

Colour controlled image generation and manipulation are of interest to artists and graphic designers. Vector Quantised Variational AutoEncoders (VQ-VAEs) with autoregressive (AR) prior are able to produce high quality images, but lack an explicit representation mechanism to control colour attributes. We introduce DualVAE, a hybrid representation model that provides such control by learning disentangled representations for colour and geometry. The geometry is represented by an image intensity mapping that identifies structural features. The disentangled representation is obtained by two novel mechanisms: (i) a dual branch architecture that separates image colour attributes from geometric attributes, and (ii) a new ELBO that trains the combined colour and geometry representations. DualVAE can control the colour of generated images, and recolour existing images by transferring the colour latent representation obtained from an exemplar image. We demonstrate that DualVAE generates images with FID nearly two times better than VQ-GAN on a diverse collection of datasets, including animated faces, logos and artistic landscapes.