High-resolution digital images are usually downscaled to fit various display
screens or save the cost of storage and bandwidth, meanwhile the post-upscaling
is adpoted to recover the original resolutions or the details in the zoom-in
images. However, typical image downscaling is a non-injective mapping due to
the loss of high-frequency information, which leads to the ill-posed problem of
the inverse upscaling procedure and poses great challenges for recovering
details from the downscaled low-resolution images. Simply upscaling with image
super-resolution methods results in unsatisfactory recovering performance. In
this work, we propose to solve this problem by modeling the downscaling and
upscaling processes from a new perspective, i.e. an invertible bijective
transformation, which can largely mitigate the ill-posed nature of image
upscaling. We develop an Invertible Rescaling Net (IRN) with deliberately
designed framework and objectives to produce visually-pleasing low-resolution
images and meanwhile capture the distribution of the lost information using a
latent variable following a specified distribution in the downscaling process.
In this way, upscaling is made tractable by inversely passing a randomly-drawn
latent variable with the low-resolution image through the network. Experimental
results demonstrate the significant improvement of our model over existing
methods in terms of both quantitative and qualitative evaluations of image
upscaling reconstruction from downscaled images.

本文提出了一种新的、基于可逆双射转换的图像下采样和上采样建模方法，使用一种随机生成的潜向量来反向生成指定分布的下采样信息，提高了降采样图像的上采样表现。通过定量和定性的图像重建评估，证明了该方法在图像上采样重建方面相比现有方法有显著的改进。

可逆图像重缩放

Invertible Image Rescaling

We introduce a novel deep-learning architecture for image upscaling by large
factors (e.g. 4x, 8x) based on examples of pristine high-resolution images. Our
target is to reconstruct high-resolution images from their downscale versions.
The proposed system performs a multi-level progressive upscaling, starting from
small factors (2x) and updating for higher factors (4x and 8x). The system is
recursive as it repeats the same procedure at each level. It is also residual
since we use the network to update the outputs of a classic upscaler. The
network residuals are improved by Iterative Back-Projections (IBP) computed in
the features of a convolutional network. To work in multiple levels we extend
the standard back-projection algorithm using a recursion analogous to
Multi-Grid algorithms commonly used as solvers of large systems of linear
equations. We finally show how the network can be interpreted as a standard
upsampling-and-filter upscaler with a space-variant filter that adapts to the
geometry. This approach allows us to visualize how the network learns to
upscale. Finally, our system reaches state of the art quality for models with
relatively few number of parameters.

本文介绍了一种基于深度学习的图像放大方法，采用逐层递进的递归算法和迭代反向投影算法 (IBP) 对低分辨率图像进行放大处理，然后通过卷积网络的特征提取过程进行修正，使得该方法在较少参数的情况下能够达到最先进的效果。