Edit-aware RAW Reconstruction
Abhijith Punnappurath, Luxi Zhao, Ke Zhao, Hue Nguyen, Radek Grzeszczuk, Michael S. Brown

TL;DR
This paper proposes an edit-aware loss function for RAW reconstruction that enhances robustness to diverse editing styles by simulating realistic camera processing pipelines during training.
Contribution
It introduces a modular, differentiable ISP-based loss that improves RAW reconstruction quality and edit-fidelity across various editing conditions and existing methods.
Findings
Improves sRGB reconstruction quality by up to 2 dB PSNR.
Enhances robustness of RAW recovery under diverse editing styles.
Enables fine-tuning of RAW reconstruction methods for specific edits.
Abstract
Users frequently edit camera images post-capture to achieve their preferred photofinishing style. While editing in the RAW domain provides greater accuracy and flexibility, most edits are performed on the camera's display-referred output (e.g., 8-bit sRGB JPEG) since RAW images are rarely stored. Existing RAW reconstruction methods can recover RAW data from sRGB images, but these approaches are typically optimized for pixel-wise RAW reconstruction fidelity and tend to degrade under diverse rendering styles and editing operations. We introduce a plug-and-play, edit-aware loss function that can be integrated into any existing RAW reconstruction framework to make the recovered RAWs more robust to different rendering styles and edits. Our loss formulation incorporates a modular, differentiable image signal processor (ISP) that simulates realistic photofinishing pipelines with tunable…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
