论文标题
联合超分辨率和反音调映射：特征分解聚合网络和新的基准测试
Joint Super-Resolution and Inverse Tone-Mapping: A Feature Decomposition Aggregation Network and A New Benchmark
论文作者
论文摘要
关节超分辨率和逆音图（关节SR-ITM）旨在增加低分辨率和标准动态范围图像的分辨率和动态范围。最近的网络主要求助于具有复杂多分支体系结构的图像分解技术。但是，固定的分解技术将在很大程度上限制了它们在多功能图像上的力量。为了利用分解机制的潜在功能，在本文中，我们将其从图像域概括为更广泛的特征域。为此，我们提出了一个轻巧的特征分解聚合网络（FDAN）。特别是，我们设计了一个功能分解块（FDB），以实现细节和基本特征图的可学习分离，并通过级联FDB来开发层次特征分解组，以实现强大的多级特征分解。此外，为了更好地评估比较方法，我们为联合SR-ITM（即SRITM-4K）收集了一个大规模数据集，该数据集为强大的模型培训和评估提供了多功能方案。两个基准数据集的实验结果表明，我们的FDAN具有有效的效率，并且超过了联合SR-ITM的最先进方法。我们的FDAN和SRITM-4K数据集的代码可在https://github.com/cs-gangxu/fdan上找到。
Joint Super-Resolution and Inverse Tone-Mapping (joint SR-ITM) aims to increase the resolution and dynamic range of low-resolution and standard dynamic range images. Recent networks mainly resort to image decomposition techniques with complex multi-branch architectures. However, the fixed decomposition techniques would largely restricts their power on versatile images. To exploit the potential power of decomposition mechanism, in this paper, we generalize it from the image domain to the broader feature domain. To this end, we propose a lightweight Feature Decomposition Aggregation Network (FDAN). In particular, we design a Feature Decomposition Block (FDB) to achieve learnable separation of detail and base feature maps, and develop a Hierarchical Feature Decomposition Group by cascading FDBs for powerful multi-level feature decomposition. Moreover, to better evaluate the comparison methods, we collect a large-scale dataset for joint SR-ITM, i.e., SRITM-4K, which provides versatile scenarios for robust model training and evaluation. Experimental results on two benchmark datasets demonstrate that our FDAN is efficient and outperforms state-of-the-art methods on joint SR-ITM. The code of our FDAN and the SRITM-4K dataset are available at https://github.com/CS-GangXu/FDAN.
