Learning Convolutional Networks for Content-weighted Image Compression

by   Mu Li, et al.
Harbin Institute of Technology
The Hong Kong Polytechnic University

Lossy image compression is generally formulated as a joint rate-distortion optimization to learn encoder, quantizer, and decoder. However, the quantizer is non-differentiable, and discrete entropy estimation usually is required for rate control. These make it very challenging to develop a convolutional network (CNN)-based image compression system. In this paper, motivated by that the local information content is spatially variant in an image, we suggest that the bit rate of the different parts of the image should be adapted to local content. And the content aware bit rate is allocated under the guidance of a content-weighted importance map. Thus, the sum of the importance map can serve as a continuous alternative of discrete entropy estimation to control compression rate. And binarizer is adopted to quantize the output of encoder due to the binarization scheme is also directly defined by the importance map. Furthermore, a proxy function is introduced for binary operation in backward propagation to make it differentiable. Therefore, the encoder, decoder, binarizer and importance map can be jointly optimized in an end-to-end manner by using a subset of the ImageNet database. In low bit rate image compression, experiments show that our system significantly outperforms JPEG and JPEG 2000 by structural similarity (SSIM) index, and can produce the much better visual result with sharp edges, rich textures, and fewer artifacts.


page 3

page 7

page 8

page 11


Learning Content-Weighted Deep Image Compression

Learning-based lossy image compression usually involves the joint optimi...

Layered Image Compression using Scalable Auto-encoder

This paper presents a novel convolutional neural network (CNN) based ima...

Deep Learning-based Image Compression with Trellis Coded Quantization

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

A GAN-based Tunable Image Compression System

The method of importance map has been widely adopted in DNN-based lossy ...

End-to-end Optimized Image Compression

We describe an image compression method, consisting of a nonlinear analy...

End-to-end optimized image compression for machines, a study

An increasing share of image and video content is analyzed by machines r...

Image-Dependent Local Entropy Models for Learned Image Compression

The leading approach for image compression with artificial neural networ...

Please sign up or login with your details

Forgot password? Click here to reset