# PixColor: Pixel Recursive Colorization

arXiv: https://arxiv.org/abs/1705.07208 · HTML: https://mlsanity.com/paper/1705.07208/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2017.

## Built on by (most cited first, 30 of 32)

- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Colorization Transformer](https://mlsanity.com/paper/2102.04432/) (2021)
- [UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes](https://mlsanity.com/paper/2205.10337/) (2022)
- [Towards Vivid and Diverse Image Colorization with Generative Color Prior](https://mlsanity.com/paper/2108.08826/) (2021)
- [Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration](https://mlsanity.com/paper/2410.00418/) (2024)
- [PalGAN: Image Colorization with Palette Generative Adversarial Networks](https://mlsanity.com/paper/2210.11204/) (2022)
- [Improved Diffusion-based Image Colorization via Piggybacked Models](https://mlsanity.com/paper/2304.11105/) (2023)
- [VCGAN: Video Colorization with Hybrid Generative Adversarial Network](https://mlsanity.com/paper/2104.12357/) (2021)
- [Video Colorization with Pre-trained Text-to-Image Diffusion Models](https://mlsanity.com/paper/2306.01732/) (2023)
- [Follow-Your-Color: Multi-Instance Sketch Colorization](https://mlsanity.com/paper/2503.16948/) (2025)
- [The Perception-Robustness Tradeoff in Deterministic Image Restoration](https://mlsanity.com/paper/2311.09253/) (2023)
- [Colorizing Monochromatic Radiance Fields](https://mlsanity.com/paper/2402.12184/) (2024)
- [Automatic Controllable Colorization via Imagination](https://mlsanity.com/paper/2404.05661/) (2024)
- [L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priors](https://mlsanity.com/paper/2305.15217/) (2023)
- [StyleFlow For Content-Fixed Image to Image Translation](https://mlsanity.com/paper/2207.01909/) (2022)
- [SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation](https://mlsanity.com/paper/2303.11591/) (2023)
- [DiffColor: Toward High Fidelity Text-Guided Image Colorization with Diffusion Models](https://mlsanity.com/paper/2308.01655/) (2023)
- [Brighten-and-Colorize: A Decoupled Network for Customized Low-Light Image Enhancement](https://mlsanity.com/paper/2308.03029/) (2023)
- [Attention-based Stylisation for Exemplar Image Colourisation](https://mlsanity.com/paper/2105.01705/) (2021)
- [Perceptual Fairness in Image Restoration](https://mlsanity.com/paper/2405.13805/) (2024)
- [TUCaN: Progressively Teaching Colourisation to Capsules](https://mlsanity.com/paper/2106.15176/) (2021)
- [Disentangled Unsupervised Image Translation via Restricted Information Flow](https://mlsanity.com/paper/2111.13279/) (2021)
- [Analysis of Different Losses for Deep Learning Image Colorization](https://mlsanity.com/paper/2204.02980/) (2022)
- [An Analysis of Generative Methods for Multiple Image Inpainting](https://mlsanity.com/paper/2205.02146/) (2022)
- [Unsupervised Structure-Consistent Image-to-Image Translation](https://mlsanity.com/paper/2208.11546/) (2022)
- [Collaboration among Image and Object Level Features for Image Colourisation](https://mlsanity.com/paper/2101.07576/) (2021)
- [Astronomical Image Colorization and upscaling with Generative Adversarial Networks](https://mlsanity.com/paper/2112.13865/) (2021)
- [Influence of Color Spaces for Deep Learning Image Colorization](https://mlsanity.com/paper/2204.02850/) (2022)
- [Human vs Objective Evaluation of Colourisation Performance](https://mlsanity.com/paper/2204.05200/) (2022)
- [ParaColorizer: Realistic Image Colorization using Parallel Generative Networks](https://mlsanity.com/paper/2208.08295/) (2022)

## Abstract (arXiv)

We propose a novel approach to automatically produce multiple colorized versions of a grayscale image. Our method results from the observation that the task of automated colorization is relatively easy given a low-resolution version of the color image. We first train a conditional PixelCNN to generate a low resolution color for a given grayscale image. Then, given the generated low-resolution color image and the original grayscale image as inputs, we train a second CNN to generate a high-resolution colorization of an image. We demonstrate that our approach produces more diverse and plausible colorizations than existing methods, as judged by human raters in a "Visual Turing Test".