Deep learning has opened up new possibilities for light field super-resolution (SR), but existing methods trained on synthetic datasets with simple degradations (e.g., bicubic downsampling) suffer from poor performance when applied to complex real-world scenarios. To address this problem, we introduce LytroZoom, the first real-world light field SR dataset capturing paired low- and high-resolution light fields of diverse indoor and outdoor scenes using a Lytro ILLUM camera. Additionally, we propose the Omni-Frequency Projection Network (OFPNet), which decomposes the omni-frequency components and iteratively enhances them through frequency projection operations to address spatially variant degradation processes present in all frequency components. Experiments demonstrate that models trained on LytroZoom outperform those trained on synthetic datasets and are generalizable to diverse content and devices. Quantitative and qualitative evaluations verify the superiority of OFPNet. We believe this work will inspire future research in real-world light field SR.

翻译：深度学习为光场超分辨率（SR）开辟了新的可能性，但现有方法在合成数据集上训练，且仅处理简单退化（如双三次下采样），应用于复杂真实场景时性能不佳。为解决这一问题，我们引入了LytroZoom——首个真实世界光场超分辨率数据集，该数据集使用Lytro ILLUM相机采集了包含室内外多样场景的成对低分辨率与高分辨率光场。此外，我们提出了全频投影网络（OFPNet），该网络通过分解全频分量，并利用频率投影操作迭代增强这些分量，以处理存在于所有频率分量中的空间变异退化过程。实验表明，在LytroZoom上训练的模型性能优于在合成数据集上训练的模型，且能泛化至多样化的内容与设备。定性和定量评估均验证了OFPNet的优越性。我们相信这项研究将启发未来真实世界光场超分辨率的研究。