DeepAI AI Chat
Log In Sign Up

Learning to Structure an Image with Few Colors

by   Yunzhong Hou, et al.
Australian National University

Color and structure are the two pillars that construct an image. Usually, the structure is well expressed through a rich spectrum of colors, allowing objects in an image to be recognized by neural networks. However, under extreme limitations of color space, the structure tends to vanish, and thus a neural network might fail to understand the image. Interested in exploring this interplay between color and structure, we study the scientific problem of identifying and preserving the most informative image structures while constraining the color space to just a few bits, such that the resulting image can be recognized with possibly high accuracy. To this end, we propose a color quantization network, ColorCNN, which learns to structure the images from the classification loss in an end-to-end manner. Given a color space size, ColorCNN quantizes colors in the original image by generating a color index map and an RGB color palette. Then, this color-quantized image is fed to a pre-trained task network to evaluate its performance. In our experiment, with only a 1-bit color space (i.e., two colors), the proposed network achieves 82.1 accuracy on the CIFAR10 dataset, outperforming traditional color quantization methods by a large margin. For applications, when encoded with PNG, the proposed color quantization shows superiority over other image compression methods in the extremely low bit-rate regime. The code is available at:


page 1

page 2

page 3

page 5

page 6


Multiple Hypothesis Colorization

In this work we focus on the problem of colorization for image compressi...

Color Sails: Discrete-Continuous Palettes for Deep Color Exploration

We present color sails, a discrete-continuous color gamut representation...

GamutMLP: A Lightweight MLP for Color Loss Recovery

Cameras and image-editing software often process images in the wide-gamu...

BigColor: Colorization using a Generative Color Prior for Natural Images

For realistic and vivid colorization, generative priors have recently be...

Understanding the Effect of Smartphone Cameras on Estimating Munsell Soil Colors from Imagery

The Munsell soil color chart (MSCC) is a in laboratories under controlle...

Differentiable JPEG: The Devil is in the Details

JPEG remains one of the most widespread lossy image coding methods. Howe...

Nonparametric Data Analysis on the Space of Perceived Colors

Moving around in a 3D world, requires the visual system of a living indi...