论文标题
拓扑损失函数：在低光数据集上进行图像deno
A Topological Loss Function: Image Denoising on a Low-Light Dataset
论文作者
论文摘要
尽管图像denoing算法吸引了大量的研究注意力，但令人惊讶的是，在实际弱光条件下获得的图像中获得的噪声很少或评估。此外，通常认为噪声特性是空间不变的，导致边缘和纹理变形后。在这里，我们介绍了一种基于持续同源性的新型拓扑损失函数。该方法在图像贴片的空间中执行，其中计算拓扑不变的，并在持久图中表示。损失功能是$ \ ell_1 $或$ \ ell_2 $损失的组合，基于新的持久性拓扑损失。我们比较了其在流行的DeNoing架构和损失功能中的性能，在我们在低光条件下捕获的自然图像的新综合数据集中训练网络 - BVI-Lowlight。分析表明，这种方法的表现优于现有方法，很好地适应了复杂的结构并抑制了常见的伪影。
Although image denoising algorithms have attracted significant research attention, surprisingly few have been proposed for, or evaluated on, noise from imagery acquired under real low-light conditions. Moreover, noise characteristics are often assumed to be spatially invariant, leading to edges and textures being distorted after denoising. Here, we introduce a novel topological loss function which is based on persistent homology. The method performs in the space of image patches, where topological invariants are calculated and represented in persistent diagrams. The loss function is a combination of $\ell_1$ or $\ell_2$ losses with the new persistence-based topological loss. We compare its performance across popular denoising architectures and loss functions, training the networks on our new comprehensive dataset of natural images captured in low-light conditions -- BVI-LOWLIGHT. Analysis reveals that this approach outperforms existing methods, adapting well to complex structures and suppressing common artifacts.
