Loading [MathJax]/extensions/MathMenu.js
Image Shooting Parameter-Guided Cascade Image Retouching Network: Think Like an Artist | IEEE Journals & Magazine | IEEE Xplore

Image Shooting Parameter-Guided Cascade Image Retouching Network: Think Like an Artist


Abstract:

Photo retouching aims to adjust the hue, luminance, contrast, and saturation of the image to make it more human and aesthetically desirable. Based on researches on image ...Show More

Abstract:

Photo retouching aims to adjust the hue, luminance, contrast, and saturation of the image to make it more human and aesthetically desirable. Based on researches on image imaging process and artists' retouching processes, we propose three improvements to existing automatic retouching methods. Firstly, in the past retouching methods, all the imaging conditions in EXIF were ignored. According to this, we design a simple module to introduce these imaging conditions into a network called ECM (EXIF Condition Module). This module can improve the performance of several existing auto-retouching methods with only a small parameter cost. Additionally, artists' operations also were ignored. By investigating artists' operations in retouching, we propose a two-stage network that brightens images first and then enriches them in the chrominance plane to mimic artists. Finally, we find that there is a color imbalance in the existing retouching dataset, thus, hue palette loss is designed to resolve the imbalance and make the image more vibrant. Experimental results show that our method is effective on the benchmark MIT-Adobe FiveK dataset and PPR10 K dataset, and achieves SOTA performance in both quantitative and qualitative evaluation.
Published in: IEEE Transactions on Multimedia ( Volume: 27)
Page(s): 1566 - 1573
Date of Publication: 23 December 2024

ISSN Information:

No metrics found for this document.

I. Related Work

Bychkovsky et al. [9] constructed a large widely used image retouching dataset MIT-Adobe FiveK. A deep learning-based method was proposed by Yan et al. in 2016 [10], since then, deep neural network-based approaches have been adopted. Roughly speaking they can be divided into two types: global-based and local-based. The former algorithms focus on overall adjustments, these methods can be divided into curve-based [8], [11], table based [12], [13], [14], and other global coefficient adjustment methods [15], [16], [17], [18], [19], [20]. Local-based methods [21], [22], [23], [24], [25], [26], [27], [28] adjust the image at the pixel level.

Usage
Select a Year
2025

View as

Total usage sinceDec 2024:52
051015202530JanFebMarAprMayJunJulAugSepOctNovDec4629000000000
Year Total:39
Data is updated monthly. Usage includes PDF downloads and HTML views.

Contact IEEE to Subscribe

References

References is not available for this document.