Enabling Region-Specific Control via Lassos in Point-Based Colorization

TL;DR

This paper introduces a lasso tool for point-based image colorization that improves control over color boundaries, reduces color collapse, and enhances efficiency compared to traditional point hints.

Contribution

It proposes a novel lasso-based control mechanism and a framework to localize attention masks, addressing color collapse in point-based colorization.

Findings

Lasso control matches the effectiveness of multiple point hints.

Reduces colorization time by 30%.

Improves boundary precision in colorization results.

Abstract

Point-based interactive colorization techniques allow users to effortlessly colorize grayscale images using user-provided color hints. However, point-based methods often face challenges when different colors are given to semantically similar areas, leading to color intermingling and unsatisfactory results-an issue we refer to as color collapse. The fundamental cause of color collapse is the inadequacy of points for defining the boundaries for each color. To mitigate color collapse, we introduce a lasso tool that can control the scope of each color hint. Additionally, we design a framework that leverages the user-provided lassos to localize the attention masks. The experimental results show that using a single lasso is as effective as applying 4.18 individual color hints and can achieve the desired outcomes in 30% less time than using points alone.