Deep learning based methods have achieved remarkable success in image
restoration and enhancement, but most such methods rely on RGB input images.
These methods fail to take into account the rich spectral distribution of
natural images. We propose a deep architecture, SpecNet, which computes
spectral profile to estimate pixel-wise dynamic range adjustment of a given
image. First, we employ an unpaired cycle-consistent framework to generate
hyperspectral images (HSI) from low-light input images. HSI is further used to
generate a normal light image of the same scene. We incorporate a
self-supervision and a spectral profile regularization network to infer a
plausible HSI from an RGB image. We evaluate the benefits of optimizing the
spectral profile for real and fake images in low-light conditions on the LOL
Dataset.

通过深度学习，提出了一种 SpecNet 深度架构，该架构计算光谱剖面以估计给定图像的像素动态范围调整，进而实现在低光条件下用环境一致框架生成高光谱图像，并通过自我监督和光谱剖面规则化网络来从 RGB 图像推断出可能的高光谱图像。

通过高光谱域映射学习提高视觉质量

Learning to Enhance Visual Quality via Hyperspectral Domain Mapping

On complete, non-compact manifolds and infinite graphs, Faber-Krahn
inequalities have been used to estimate the rate of decay of the heat kernel.
We develop this technique in the setting of finite Markov chains, proving upper
and lower mixing time bounds via the spectral profile. This approach lets us
recover and refine previous conductance-based bounds of mixing time (including
the Morris-Peres result), and in general leads to sharper estimates of
convergence rates. We apply this method to several models including groups with
moderate growth, the fractal-like Viscek graphs, and the torus, to obtain tight
bounds on the corresponding mixing times.

本文探讨了有限马尔科夫链的 Fabre-Krahn 不等式，证明了上下混合时间边界并获得更精细的混合时间收敛率估计，从而获得了可应用于多个模型的尖锐边界。