RAWMamba：基于状态空间模型的统一 sRGB 到 RAW 去渲染
RAWMamba: Unified sRGB-to-RAW De-rendering With State Space Model
AI总结：
本文提出基于 Mamba 的统一框架 RAWMamba，通过统一元数据嵌入和局部色调感知模块处理图像与视频的 sRGB 到 RAW 去渲染，实现最先进的高质量 RAW 数据重建。
摘要：
近期在 sRGB 到 RAW 去渲染领域的进展日益强调元数据驱动的方法，以通过 sRGB 图像并辅以部分 RAW 信息来重建 RAW 数据。在基于图像的去渲染中，元数据通常通过采样获取，而在视频任务中，通常从初始帧导出。不同的元数据需求需要专门的网络架构，导致架构不兼容，增加了部署复杂性。本文提出 RAWMamba，一个基于 Mamba 的统一框架，用于跨图像和视频领域的 sRGB 到 RAW 去渲染。其核心是统一元数据嵌入（UME）模块，将多种元数据类型协调为统一表示。具体而言，提出多视角亲和建模方法以促进参考信息的提取。此外，引入局部色调感知 Mamba（LTA-Mamba）模块，捕获长距离依赖以实现元数据的有效全局传播。实验结果表明，所提出的 RAWMamba 实现了最先进的性能，生成了高质量的 RAW 数据重建。
英文摘要：
Recent advancements in sRGB-to-RAW de-rendering have increasingly emphasized metadata-driven approaches to reconstruct RAW data from sRGB images, supplemented by partial RAW information. In image-based de-rendering, metadata is commonly obtained through sampling, whereas in video tasks, it is typically derived from the initial frame. The distinct metadata requirements necessitate specialized network architectures, leading to architectural incompatibilities that increase deployment complexity. In this paper, we propose RAWMamba, a Mamba-based unified framework developed for sRGB-to-RAW de-rendering across both image and video domains. The core of RAWMamba is the Unified Metadata Embedding (UME) module, which harmonizes diverse metadata types into a unified representation. In detail, a multi-perspective affinity modeling method is proposed to promote the extraction of reference information. In addition, we introduce the Local Tone-Aware Mamba (LTA-Mamba) module, which captures long-range dependencies to enable effective global propagation of metadata. Experimental results demonstrate that the proposed RAWMamba achieves state-of-the-art performance, yielding high-quality RAW data reconstruction.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
