MFSR-GAN：结合手持运动建模的多帧超分辨率
MFSR-GAN: Multi-Frame Super-Resolution with Handheld Motion Modeling
AI总结：
针对真实世界手持连拍图像的噪声与运动建模问题，提出一种合成数据引擎和强调基准帧的MFSR-GAN多尺度RAW到RGB网络，实现了更清晰逼真的多帧超分辨率重建。
摘要：
智能手机相机已成为无处不在的成像工具，但其小型传感器和紧凑的光学器件通常限制了空间分辨率并引入失真。结合多幅低分辨率（LR）帧的信息以生成高分辨率（HR）图像已被探索用于克服智能手机相机的固有局限性。尽管多帧超分辨率（MFSR）前景广阔，但当前方法受到数据集的阻碍，这些数据集无法捕捉真实世界手持连拍图像中特有的噪声和运动模式。在这项工作中，我们通过引入一种新颖的合成数据引擎来解决这一差距，该引擎使用多曝光静态图像来合成LR-HR训练对，同时保留了手持连拍摄影中存在的传感器特定噪声特征和图像运动。我们还提出了MFSR-GAN：一种用于MFSR的多尺度RAW到RGB网络。与先前的方法相比，MFSR-GAN在其整个架构中强调“基准帧”以减轻伪影。在合成数据和真实数据上的实验结果表明，使用我们的合成引擎训练的MFSR-GAN比现有的真实世界MFSR方法产生了更清晰、更逼真的重建结果。
英文摘要：
Smartphone cameras have become ubiquitous imaging tools, yet their small sensors and compact optics often limit spatial resolution and introduce distortions. Combining information from multiple low-resolution (LR) frames to produce a high-resolution (HR) image has been explored to overcome the inherent limitations of smartphone cameras. Despite the promise of multi-frame super-resolution (MFSR), current approaches are hindered by datasets that fail to capture the characteristic noise and motion patterns found in real-world handheld burst images. In this work, we address this gap by introducing a novel synthetic data engine that uses multi-exposure static images to synthesize LR-HR training pairs while preserving sensor-specific noise characteristics and image motion found during handheld burst photography. We also propose MFSR-GAN: a multi-scale RAW-to-RGB network for MFSR. Compared to prior approaches, MFSR-GAN emphasizes a "base frame" throughout its architecture to mitigate artifacts. Experimental results on both synthetic and real data demonstrates that MFSR-GAN trained with our synthetic engine yields sharper, more realistic reconstructions than existing methods for real-world MFSR.
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。
