Modeling Lost Information in Lossy Image Compression

by   Yaolong Wang, et al.
Peking University

Lossy image compression is one of the most commonly used operators for digital images. Most recently proposed deep-learning-based image compression methods leverage the auto-encoder structure, and reach a series of promising results in this field. The images are encoded into low dimensional latent features first, and entropy coded subsequently by exploiting the statistical redundancy. However, the information lost during encoding is unfortunately inevitable, which poses a significant challenge to the decoder to reconstruct the original images. In this work, we propose a novel invertible framework called Invertible Lossy Compression (ILC) to largely mitigate the information loss problem. Specifically, ILC introduces an invertible encoding module to replace the encoder-decoder structure to produce the low dimensional informative latent representation, meanwhile, transform the lost information into an auxiliary latent variable that won't be further coded or stored. The latent representation is quantized and encoded into bit-stream, and the latent variable is forced to follow a specified distribution, i.e. isotropic Gaussian distribution. In this way, recovering the original image is made tractable by easily drawing a surrogate latent variable and applying the inverse pass of the module with the sampled variable and decoded latent features. Experimental results demonstrate that with a new component replacing the auto-encoder in image compression methods, ILC can significantly outperform the baseline method on extensive benchmark datasets by combining with the existing compression algorithms.


page 17

page 18

page 19

page 20


Conditional Probability Models for Deep Image Compression

Deep Neural Networks trained as image auto-encoders have recently emerge...

Deep Learning-based Image Compression with Trellis Coded Quantization

Recently many works attempt to develop image compression models based on...

Towards Conceptual Compression

We introduce a simple recurrent variational auto-encoder architecture th...

Invertible Image Rescaling

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

Invertible Rescaling Network and Its Extensions

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

Multiscale Augmented Normalizing Flows for Image Compression

Most learning-based image compression methods lack efficiency for high i...

Modeling the Biological Pathology Continuum with HSIC-regularized Wasserstein Auto-encoders

A crucial challenge in image-based modeling of biomedical data is to ide...

Please sign up or login with your details

Forgot password? Click here to reset