Sliced $\mathcal{L}_2$ Distance for Colour Grading

TL;DR

This paper introduces a novel $ ext{L}_2$ distance-based method for high-dimensional distribution mapping, specifically applied to colour transfer between images, demonstrating competitive results with existing techniques.

Contribution

It presents a new iterative projection approach for high-dimensional $ ext{L}_2$ distance mapping, applied to colour grading, with improved handling of correspondences.

Findings

Quantitative results show competitive accuracy.

Qualitative results demonstrate effective colour transfer.

Method outperforms some existing colour transfer techniques.

Abstract

We propose a new method with $\mathcal{L}_2$ distance that maps one $N$-dimensional distribution to another, taking into account available information about correspondences. We solve the high-dimensional problem in 1D space using an iterative projection approach. To show the potentials of this mapping, we apply it to colour transfer between two images that exhibit overlapped scenes. Experiments show quantitative and qualitative competitive results as compared with the state of the art colour transfer methods.