Influence of Color Spaces for Deep Learning Image Colorization

TL;DR

This paper investigates how different color spaces (RGB, YUV, Lab) influence the performance of deep learning models for image colorization, highlighting the importance of architecture design and evaluation protocols tailored to image types.

Contribution

It provides a comparative analysis of color spaces in deep learning-based colorization and emphasizes the significance of architecture and evaluation design based on image characteristics.

Findings

Qualitative and quantitative results vary across color spaces.

Designing architecture and evaluation protocols is crucial for different image types.

No clear superiority of one color space over others was established.

Abstract

Colorization is a process that converts a grayscale image into a color one that looks as natural as possible. Over the years this task has received a lot of attention. Existing colorization methods rely on different color spaces: RGB, YUV, Lab, etc. In this chapter, we aim to study their influence on the results obtained by training a deep neural network, to answer the question: "Is it crucial to correctly choose the right color space in deep-learning based colorization?". First, we briefly summarize the literature and, in particular, deep learning-based methods. We then compare the results obtained with the same deep neural network architecture with RGB, YUV and Lab color spaces. Qualitative and quantitative analysis do not conclude similarly on which color space is better. We then show the importance of carefully designing the architecture and evaluation protocols depending on the types of images that are being processed and their specificities: strong/small contours, few/many objects, recent/archive images.