Learning Content-Weighted Deep Image Compression

by   Mu Li, et al.
ETH Zurich
The Chinese University of Hong Kong, Shenzhen
The Hong Kong Polytechnic University

Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance. Most existing methods adopt spatially invariant bit length allocation and incorporate discrete entropy approximation to constrain compression rate. Nonetheless, the information content is spatially variant, where the regions with complex and salient structures generally are more essential to image compression. Taking the spatial variation of image content into account, this paper presents a content-weighted encoder-decoder model, which involves an importance map subnet to produce the importance mask for locally adaptive bit rate allocation. Consequently, the summation of importance mask can thus be utilized as an alternative of entropy estimation for compression rate control. Furthermore, the quantized representations of the learned code and importance map are still spatially dependent, which can be losslessly compressed using arithmetic coding. To compress the codes effectively and efficiently, we propose a trimmed convolutional network to predict the conditional probability of quantized codes. Experiments show that the proposed method can produce visually much better results, and performs favorably in comparison with deep and traditional lossy image compression approaches.


page 2

page 4

page 5

page 11

page 12

page 13

page 15


Learning Convolutional Networks for Content-weighted Image Compression

Lossy image compression is generally formulated as a joint rate-distorti...

Spatially adaptive image compression using a tiled deep network

Deep neural networks represent a powerful class of function approximator...

Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks

We propose a method for lossy image compression based on recurrent, conv...

A GAN-based Tunable Image Compression System

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

Efficient Trimmed Convolutional Arithmetic Encoding for Lossless Image Compression

Arithmetic encoding is an essential class of coding techniques which hav...

SigVIC: Spatial Importance Guided Variable-Rate Image Compression

Variable-rate mechanism has improved the flexibility and efficiency of l...

DSIC: Deep Stereo Image Compression

In this paper we tackle the problem of stereo image compression, and lev...

Please sign up or login with your details

Forgot password? Click here to reset