基于小波循环重建的任意尺度RAW图像降尺度学习
Learning Arbitrary-Scale RAW Image Downscaling with Wavelet-based Recurrent Reconstruction
AI总结：
针对RAW图像缺乏专用降尺度框架的问题，提出基于小波的循环重建框架及配套模块与损失函数，构建多尺度基准数据集，实现了性能更优的任意尺度RAW图像降尺度。
摘要：
图像降尺度对高分辨率（HR）图像的高效存储与传输至关重要。现有基于学习的方法聚焦于sRGB域内的降尺度操作，通常存在细节模糊与非预期伪影的问题。RAW图像携带着未处理的光子信息，具备更高的灵活性，但缺乏专门的降尺度框架。本文提出一种基于小波的循环重建框架，利用小波变换的信息无损特性，以从粗到细的方式实现任意尺度的RAW图像降尺度；其中设计了低频任意尺度降尺度模块（LASDM）和高频预测模块（HFPM），以保障重建后的低分辨率（LR）RAW图像的结构与纹理完整性，同时引入能量最大化损失来对齐HR与LR域之间的高频能量。此外，我们构建了真实非整数RAW降尺度（Real-NIRD）数据集，其包含1.3×的非整数降尺度因子，并将该数据集与公开的整数倍（2×、3×、4×）降尺度数据集结合，用于任意尺度图像降尺度的综合基准测试。大量实验表明，本文方法在定量指标与视觉效果上均优于现有最先进的对比方法。代码与数据集将发布于https://github.com/RenYangSCU/ASRD。
英文摘要：
Image downscaling is critical for efficient storage and transmission of high-resolution (HR) images. Existing learning-based methods focus on performing downscaling within the sRGB domain, which typically suffers from blurred details and unexpected artifacts. RAW images, with their unprocessed photonic information, offer greater flexibility but lack specialized downscaling frameworks. In this paper, we propose a wavelet-based recurrent reconstruction framework that leverages the information lossless attribute of wavelet transformation to fulfill the arbitrary-scale RAW image downscaling in a coarse-to-fine manner, in which the Low-Frequency Arbitrary-Scale Downscaling Module (LASDM) and the High-Frequency Prediction Module (HFPM) are proposed to preserve structural and textural integrity of the reconstructed low-resolution (LR) RAW images, alongside an energy-maximization loss to align high-frequency energy between HR and LR domain. Furthermore, we introduce the Realistic Non-Integer RAW Downscaling (Real-NIRD) dataset, featuring a non-integer downscaling factor of 1.3$\times$, and incorporate it with publicly available datasets with integer factors (2$\times$, 3$\times$, 4$\times$) for comprehensive benchmarking arbitrary-scale image downscaling purposes. Extensive experiments demonstrate that our method outperforms existing state-of-the-art competitors both quantitatively and visually. The code and dataset will be released at https://github.com/RenYangSCU/ASRD.
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。
