Benchmarking RAW and RGB Restoration in Image Signal Processors

• URL: http://arxiv.org/abs/2609.02831v1
• Date: Wed, 02 Sep 2026 17:15:44 GMT
• Title: Benchmarking RAW and RGB Restoration in Image Signal Processors
• Abstract summary: Modern cameras transform RAW sensor measurements into sRGB images through an image signal processor (ISP)<n>We benchmark two placements for blind restoration around a fixed ISP.<n>Our results show that placement alone does not determine performance.
• Score: 58.613429740440324
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Modern cameras transform RAW sensor measurements into sRGB images through an image signal processor (ISP). We benchmark two placements for blind restoration around a fixed ISP: (A) pre-ISP restoration in the RAW domain and (B) post-ISP restoration in the sRGB domain. The benchmark covers four smartphone device groups, two learned ISPs, three degradation regimes--noise, blur, and joint noise and blur--, and several representative RAW and RGB restoration models. Our results show that placement alone does not determine performance. The RAW restoration strategy outperforms the best generic RGB restoration models. However, RGB restoration models trained considering the ISP transformations, achieve the best overall performance. Our novel benchmark demonstrates that the image reconstruction performance strongly depends on the alignment between the restoration model and the target imaging pipeline. We consequently recommend reporting restoration placement and ISP-aware supervision as key experimental factors. Our code is available at https://github.com/mv-lab/AISP

Related papers

• $\mathbf{R}^3$: Reconstruction, Raw, and Rain: Deraining Directly in the Bayer Domain [5.193141021890106]
  Most reconstruction networks are trained on post-ISP sRGB images, even though the image-signal-processing pipeline irreversibly mixes colors, clips dynamic range, and blurs fine detail.<n>This paper uses the rain degradation problem as a use case to show that these losses are avoidable, and demonstrates that learning directly on raw Bayer mosaics yields superior reconstructions.
  arXiv  Detail & Related papers  (2025-09-28T18:31:24Z)
• RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report [80.64928431399075]
  This paper covers the second challenge on RAW Reconstruction from sRGB (Reverse ISP)<n>We aim to recover RAW sensor images from smartphones given the corresponding sRGB images without metadata.
  arXiv  Detail & Related papers  (2025-06-02T17:58:31Z)
• Toward Efficient Deep Blind RAW Image Restoration [56.41827271721955]
  We design a new realistic degradation pipeline for training deep blind RAW restoration models. Our pipeline considers realistic sensor noise, motion blur, camera shake, and other common degradations. The models trained with our pipeline and data from multiple sensors, can successfully reduce noise and blur, and recover details in RAW images captured from different cameras.
  arXiv  Detail & Related papers  (2024-09-26T18:34:37Z)
• BSRAW: Improving Blind RAW Image Super-Resolution [63.408484584265985]
  We tackle blind image super-resolution in the RAW domain. We design a realistic degradation pipeline tailored specifically for training models with raw sensor data. Our BSRAW models trained with our pipeline can upscale real-scene RAW images and improve their quality.
  arXiv  Detail & Related papers  (2023-12-24T14:17:28Z)
• Image Demoireing in RAW and sRGB Domains [18.921026683632146]
  We develop Skip-Connection-based Demoireing Module (SCDM) with Gated Feedback Module (GFM) and Frequency Selection Module (FSM) We design a RGB Guided ISP (RGISP) to learn a device-dependent ISP, assisting the process of color recovery. 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.
  arXiv  Detail & Related papers  (2023-12-14T16:00:28Z)
• Self-Supervised Reversed Image Signal Processing via Reference-Guided Dynamic Parameter Selection [1.1602089225841632]
  We propose a self-supervised reversed ISP method that does not require metadata and paired images. The proposed method converts a RGB image into a RAW-like image taken in the same environment with the same sensor as a reference RAW image. We show that the proposed method is able to learn various reversed ISPs with comparable accuracy to other state-of-the-art supervised methods.
  arXiv  Detail & Related papers  (2023-03-24T11:12:05Z)
• Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report [109.2135194765743]
  This paper introduces the AIM 2022 Challenge on Reversed Image Signal Processing and RAW Reconstruction. We aim to recover raw sensor images from the corresponding RGBs without metadata and, by doing this, "reverse" the ISP transformation.
  arXiv  Detail & Related papers  (2022-10-20T10:43:53Z)
• Reversing Image Signal Processors by Reverse Style Transferring [3.867363075280544]
  We seek an answer to the question: Can the ISP operations be modeled as the style factor in an end-to-end learning pipeline? We propose a novel architecture, namely RST-ISP-Net, for learning to reverse the ISP operations with the help of adaptive feature normalization.
  arXiv  Detail & Related papers  (2022-10-17T13:21:37Z)
• Learning sRGB-to-Raw-RGB De-rendering with Content-Aware Metadata [46.28281823015191]
  We show how to improve the de-rendering results by jointly learning sampling and reconstruction. Our experiments show that our learned sampling can adapt to the image content to produce better raw reconstructions than existing methods.
  arXiv  Detail & Related papers  (2022-06-03T20:43:17Z)
• Towards Low Light Enhancement with RAW Images [101.35754364753409]
  We make the first benchmark effort to elaborate on the superiority of using RAW images in the low light enhancement. We develop a new evaluation framework, Factorized Enhancement Model (FEM), which decomposes the properties of RAW images into measurable factors. A RAW-guiding Exposure Enhancement Network (REENet) is developed, which makes trade-offs between the advantages and inaccessibility of RAW images in real applications.
  arXiv  Detail & Related papers  (2021-12-28T07:27:51Z)
• Semantic-embedded Unsupervised Spectral Reconstruction from Single RGB Images in the Wild [48.44194221801609]
  We propose a new lightweight and end-to-end learning-based framework to tackle this challenge. We progressively spread the differences between input RGB images and re-projected RGB images from recovered HS images via effective camera spectral response function estimation. Our method significantly outperforms state-of-the-art unsupervised methods and even exceeds the latest supervised method under some settings.
  arXiv  Detail & Related papers  (2021-08-15T05:19:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.