Boosting Real-World Super-Resolution with RAW Data: a New Perspective, Dataset and Baseline
Keywords: Real-World Super-Resolution, RAW Data
TL;DR: This paper introduces RealSR-RAW, a dataset with over 10,000 paired LR and HR RGB images and corresponding LR RAW data, and pioneers a novel RAW adapter using RAW data to enhance Real SR model performance.
Abstract: Real-world image super-resolution (Real SR) aims to generate high-fidelity, detail-rich high-resolution (HR) images from low-resolution (LR) counterparts. Existing Real SR methods primarily focus on processing within the RGB domain. In this paper, we pioneer the use of detail-rich RAW data to complement RGB-only Real SR, specifically by utilizing both LR RGB and RAW inputs to generate superior HR RGB outputs. We argue that key image processing steps in Image Signal Processing, such as denoising and demosaicing, inherently result in the loss of fine details, making RAW data a valuable information source. To validate this, we present RealSR-RAW, a comprehensive dataset comprising 10,000 pairs with LR and HR RGB images, along with corresponding LR RAW data, captured across multiple smartphones under varying focal lengths and diverse scenes. Additionally, we propose a novel, general RAW adapter to efficiently integrate RAW data into existing CNNs, Transformers, and Diffusion-based Real SR models by suppressing the noise contained in RAW and aligning distribution. Extensive experiments demonstrate that incorporating RAW data significantly enhances detail recovery and improves Real SR performance across ten evaluation metrics, including both fidelity and perception-oriented metrics. Our findings open a new direction for the Real SR task, with the dataset and code made available to support future research.
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 831
Loading