Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling

by   Jinhai Yang, et al.

High-resolution (HR) images are usually downscaled to low-resolution (LR) ones for better display and afterward upscaled back to the original size to recover details. Recent work in image rescaling formulates downscaling and upscaling as a unified task and learns a bijective mapping between HR and LR via invertible networks. However, in real-world applications (e.g., social media), most images are compressed for transmission. Lossy compression will lead to irreversible information loss on LR images, hence damaging the inverse upscaling procedure and degrading the reconstruction accuracy. In this paper, we propose the Self-Asymmetric Invertible Network (SAIN) for compression-aware image rescaling. To tackle the distribution shift, we first develop an end-to-end asymmetric framework with two separate bijective mappings for high-quality and compressed LR images, respectively. Then, based on empirical analysis of this framework, we model the distribution of the lost information (including downscaling and compression) using isotropic Gaussian mixtures and propose the Enhanced Invertible Block to derive high-quality/compressed LR images in one forward pass. Besides, we design a set of losses to regularize the learned LR images and enhance the invertibility. Extensive experiments demonstrate the consistent improvements of SAIN across various image rescaling datasets in terms of both quantitative and qualitative evaluation under standard image compression formats (i.e., JPEG and WebP).


page 2

page 4

page 6

page 7


Invertible Rescaling Network and Its Extensions

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

Invertible Image Rescaling

High-resolution digital images are usually downscaled to fit various dis...

Mixed-Resolution Image Representation and Compression with Convolutional Neural Networks

In this paper, we propose a end-to-end mixed-resolution image compressio...

Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution

Due to the limits of bandwidth and storage space, digital images are usu...

Learned Lossless Compression for JPEG via Frequency-Domain Prediction

JPEG images can be further compressed to enhance the storage and transmi...

Explorable Decoding of Compressed Images

The ever-growing amounts of visual contents captured on a daily basis ne...

Neural Image Decompression: Learning to Render Better Image Previews

A rapidly increasing portion of Internet traffic is dominated by request...

Please sign up or login with your details

Forgot password? Click here to reset