从手机sRGB图像无元数据逆向还原RAW图像，提升低层视觉任务数据质量。
RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report
- 基于sRGB图像和传感器信息，逆向推导RAW图像，无需原始元数据。
- 150+参赛者提交模型，建立当前最先进的真实感RAW生成基准。
- 适用于图像增强、去噪等需线性RAW数据的低层视觉任务。
许多低层视觉任务因RAW数据具有线性特性、高比特深度和传感器设计优势，常在RAW域进行。然而，真实RAW数据集稀缺且采集成本远高于现有的大规模公开sRGB数据集。因此，众多方法尝试利用传感器信息和sRGB图像生成逼真的RAW图像。本文介绍NTIRE 2025挑战赛中关于从sRGB图像重建RAW（逆ISP）的第二项任务。目标是在不提供元数据的前提下，仅根据对应的sRGB图像恢复智能手机的RAW传感器图像，实现对ISP变换的“逆向”还原。超过150名参与者提交了高效模型，所提出的方案与基准共同确立了当前生成真实感RAW数据的最先进水平。
原文摘要 · Abstract (English)
Numerous low-level vision tasks operate in the RAW domain due to its linear properties, bit depth, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public sRGB datasets. For this reason, many approaches try to generate realistic RAW images using sensor information and sRGB images. This paper covers the second challenge on RAW Reconstruction from sRGB (Reverse ISP). We aim to recover RAW sensor images from smartphones given the corresponding sRGB images without metadata and, by doing this, ``reverse" the ISP transformation. Over 150 participants joined this NTIRE 2025 challenge and submitted efficient models. The proposed methods and benchmark establish the state-of-the-art for generating realistic RAW data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。