DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization
This work addresses the problem of practical image harmonization for users by enabling high-resolution processing and model comprehensibility, though it is incremental as it builds on existing deep learning approaches.
The paper tackles high-resolution image color harmonization by proposing a deep comprehensible color filter learning framework that learns human-interpretable neural filters, achieving 7.63% and 1.69% relative improvements in MSE and PSNR over state-of-the-art methods on the iHarmony4 dataset.
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.