Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Image Demoireing in RAW and sRGB Domains

Shuning Xu, Binbin Song, Xiangyu Chen, Xina Liu, Jiantao Zhou

TL;DR

This paper develops Skip-Connection-based Demoireing Module (SCDM) with Gated Feedback Module (GFM) and Frequency Selection Module (FSM) embedded in skip-connections for the efficient and effective demoireing of RAW and sRGB features, respectively, and designs a RGB Guided ISP (RGISP) to learn a device-dependent ISP, assisting the process of color recovery.

Abstract

Moire patterns frequently appear when capturing screens with smartphones or cameras, potentially compromising image quality. Previous studies suggest that moire pattern elimination in the RAW domain offers greater effectiveness compared to demoireing in the sRGB domain. Nevertheless, relying solely on RAW data for image demoireing is insufficient in mitigating the color cast due to the absence of essential information required for the color correction by the image signal processor (ISP). In this paper, we propose to jointly utilize both RAW and sRGB data for image demoireing (RRID), which are readily accessible in modern smartphones and DSLR cameras. We develop Skip-Connection-based Demoireing Module (SCDM) with Gated Feedback Module (GFM) and Frequency Selection Module (FSM) embedded in skip-connections for the efficient and effective demoireing of RAW and sRGB features, respectively. Subsequently, we design a RGB Guided ISP (RGISP) to learn a device-dependent ISP, assisting the process of color recovery. Extensive experiments demonstrate that our RRID outperforms state-of-the-art approaches, in terms of the performance in moire pattern removal and color cast correction by 0.62dB in PSNR and 0.003 in SSIM.

Image Demoireing in RAW and sRGB Domains

TL;DR

This paper develops Skip-Connection-based Demoireing Module (SCDM) with Gated Feedback Module (GFM) and Frequency Selection Module (FSM) embedded in skip-connections for the efficient and effective demoireing of RAW and sRGB features, respectively, and designs a RGB Guided ISP (RGISP) to learn a device-dependent ISP, assisting the process of color recovery.

Abstract

Moire patterns frequently appear when capturing screens with smartphones or cameras, potentially compromising image quality. Previous studies suggest that moire pattern elimination in the RAW domain offers greater effectiveness compared to demoireing in the sRGB domain. Nevertheless, relying solely on RAW data for image demoireing is insufficient in mitigating the color cast due to the absence of essential information required for the color correction by the image signal processor (ISP). In this paper, we propose to jointly utilize both RAW and sRGB data for image demoireing (RRID), which are readily accessible in modern smartphones and DSLR cameras. We develop Skip-Connection-based Demoireing Module (SCDM) with Gated Feedback Module (GFM) and Frequency Selection Module (FSM) embedded in skip-connections for the efficient and effective demoireing of RAW and sRGB features, respectively. Subsequently, we design a RGB Guided ISP (RGISP) to learn a device-dependent ISP, assisting the process of color recovery. Extensive experiments demonstrate that our RRID outperforms state-of-the-art approaches, in terms of the performance in moire pattern removal and color cast correction by 0.62dB in PSNR and 0.003 in SSIM.
Paper Structure (17 sections, 5 equations, 10 figures, 6 tables)

This paper contains 17 sections, 5 equations, 10 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Image and Video Demoiréing
  4. Learning-Based RAW Image Processing
  5. Methodology
  6. Design of SCDM
  7. Design of RGISP
  8. Loss Function
  9. Experiments
  10. Experimental Setup
  11. Quantitative Results
  12. Qualitative Results
  13. Ablation Study
  14. Conclusion
  15. Additional Ablation Study for SCDM
  16. ...and 2 more sections

Figures (10)

  • Figure 1: Comparison of image demoiréing in different domains. (a) Image demoiréing in sRGB domain. (b) Image demoiréing in RAW domain. (c) Our proposed RRID, which performs image demoiréing in both RAW domain and sRGB domain
  • Figure 2: The overview and detailed structures of our proposed RRID.
  • Figure 3: The structure of RGISP.
  • Figure 4: Qualitative comparison on RAW image demoiréing TMM22 dataset yue2022recaptured.
  • Figure 5: Visualization of the ablation study for architecture and inputs comparison.
  • ...and 5 more figures