DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization

TL;DR

This paper introduces DCCF, a framework for high-resolution image harmonization that learns human-understandable color filters, improving both performance and usability over existing methods.

Contribution

The paper proposes a novel deep learning framework that learns comprehensible color filters for high-resolution image harmonization, addressing practical issues of resolution and interpretability.

Findings

Outperforms state-of-the-art methods on iHarmony4 dataset.

Achieves 7.63% improvement in MSE and 1.69% in PSNR.

Provides user-friendly, interpretable filters for image editing.

Abstract

Image color harmonization algorithm aims to automatically match the color distribution of foreground and background images captured in different conditions. Previous deep learning based models neglect two issues that are critical for practical applications, namely high resolution (HR) image processing and model comprehensibility. In this paper, we propose a novel Deep Comprehensible Color Filter (DCCF) learning framework for high-resolution image harmonization. Specifically, DCCF first downsamples the original input image to its low-resolution (LR) counter-part, then learns four human comprehensible neural filters (i.e. hue, saturation, value and attentive rendering filters) in an end-to-end manner, finally applies these filters to the original input image to get the harmonized result. Benefiting from the comprehensible neural filters, we could provide a simple yet efficient handler for users to cooperate with deep model to get the desired results with very little effort when necessary. Extensive experiments demonstrate the effectiveness of DCCF learning framework and it outperforms state-of-the-art post-processing method on iHarmony4 dataset on images' full-resolutions by achieving 7.63% and 1.69% relative improvements on MSE and PSNR respectively.