DeepAI AI Chat
Log In Sign Up

Invertible Image Rescaling

by   Mingqing Xiao, et al.

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.


page 12

page 13

page 22

page 23

page 24

page 25

page 26

page 27


Invertible Rescaling Network and Its Extensions

Image rescaling is a commonly used bidirectional operation, which first ...

Enhancing Image Rescaling using Dual Latent Variables in Invertible Neural Network

Normalizing flow models have been used successfully for generative image...

Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling

High-resolution (HR) images are usually downscaled to low-resolution (LR...

Raising The Limit Of Image Rescaling Using Auxiliary Encoding

Normalizing flow models using invertible neural networks (INN) have been...

Adaptive Digital Scan Variable Pixels

The square and rectangular shape of the pixels in the digital images for...

Modeling Lost Information in Lossy Image Compression

Lossy image compression is one of the most commonly used operators for d...

Scale-arbitrary Invertible Image Downscaling

Downscaling is indispensable when distributing high-resolution (HR) imag...

Code Repositories


[ECCV 2020, IJCV 2022] Invertible Image Rescaling

view repo