Spatially adaptive image compression using a tiled deep network

02/07/2018
by   David Minnen, et al.
0

Deep neural networks represent a powerful class of function approximators that can learn to compress and reconstruct images. Existing image compression algorithms based on neural networks learn quantized representations with a constant spatial bit rate across each image. While entropy coding introduces some spatial variation, traditional codecs have benefited significantly by explicitly adapting the bit rate based on local image complexity and visual saliency. This paper introduces an algorithm that combines deep neural networks with quality-sensitive bit rate adaptation using a tiled network. We demonstrate the importance of spatial context prediction and show improved quantitative (PSNR) and qualitative (subjective rater assessment) results compared to a non-adaptive baseline and a recently published image compression model based on fully-convolutional neural networks.

READ FULL TEXT

page 1

page 4

research
03/29/2017

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...
research
04/01/2019

Learning Content-Weighted Deep Image Compression

Learning-based lossy image compression usually involves the joint optimi...
research
05/27/2019

Attention Based Image Compression Post-Processing Convolutional Neural Network

The traditional image compressors, e.g., BPG and H.266, have achieved gr...
research
08/28/2023

Entropy-based Guidance of Deep Neural Networks for Accelerated Convergence and Improved Performance

Neural networks have dramatically increased our capacity to learn from l...
research
05/15/2019

DeepCABAC: Context-adaptive binary arithmetic coding for deep neural network compression

We present DeepCABAC, a novel context-adaptive binary arithmetic coder f...
research
08/26/2016

Scalable Compression of Deep Neural Networks

Deep neural networks generally involve some layers with mil- lions of pa...
research
07/11/2022

Accelerated Deep Lossless Image Coding with Unified Paralleleized GPU Coding Architecture

We propose Deep Lossless Image Coding (DLIC), a full resolution learned ...

Please sign up or login with your details

Forgot password? Click here to reset