PixColor: Pixel Recursive Colorization

By Sergio Guadarrama, Ryan Dahl, David Bieber, Mohammad Norouzi, Jonathon Shlens, Kevin P. Murphy. 2017

114 citations recorded by the source corpus.

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".

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

The Perception-Distortion Tradeoff (2017, background): “-fake user studies, which examine the ability of human observers to tell whether x̂ is real or the output of an algorithm [48, 14, 6, 13, 49, 22, 10] (similarly to the idea underlying generative adversarial nets [9]).”
Toward Multimodal Image-to-Image Translation (2017, background): “While conditional VAEs [42] and autoregressive models [32, 33] have shown promise [16, 44, 46], imageto-image conditional GANs have lead to a substantial boost in the quality of the results.”
Palette: Image-to-Image Diffusion Models (2021, methodology): “Prior work on colorization [Guadarrama et al. 2017; Kumar et al. 2021; Zhang et al. 2016] relied on FID scores and human evaluation for model comparison.”
UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes (2022, background): “Autoregressive models gained a popularity in computer vision as (conditional) image generation tools [50, 49, 41] and later were used for tasks like image colorization [38, 14, 28].”
Learning Beyond Human Expertise with Generative Models for Dental Restorations (2018, unknown): “his task. Conditional image generation. All of the methods mentioned above can be easily conditioned. For example, conditional VAEs [29] and autoregressive models [16,17] have shown promising results [30,31,32]. Prior works have conditioned GANs [9] to tackle various image-to-image generation proble”
Colorization Transformer (2021, methodology): “For our qualitative assessment, we follow the protocol used in PixColor (Guadarrama et al., 2017).”
Guided Image Generation with Conditional Invertible Neural Networks (2019, methodology): “To compensate, modiﬁcations and extensions to generative approaches have been developed, such as auto-regressive models [12] and CRFs [34].”