DeepAI AI Chat
Log In Sign Up

A Learned Pixel-by-Pixel Lossless Image Compression Method with 59K Parameters and Parallel Decoding

by   Sinem Gumus, et al.
Middle East Technical University

This paper considers lossless image compression and presents a learned compression system that can achieve state-of-the-art lossless compression performance but uses only 59K parameters, which is more than 30x less than other learned systems proposed recently in the literature. The explored system is based on a learned pixel-by-pixel lossless image compression method, where each pixel's probability distribution parameters are obtained by processing the pixel's causal neighborhood (i.e. previously encoded/decoded pixels) with a simple neural network comprising 59K parameters. This causality causes the decoder to operate sequentially, i.e. the neural network has to be evaluated for each pixel sequentially, which increases decoding time significantly with common GPU software and hardware. To reduce the decoding time, parallel decoding algorithms are proposed and implemented. The obtained lossless image compression system is compared to traditional and learned systems in the literature in terms of compression performance, encoding-decoding times and computational complexity.


page 1

page 4

page 5


Learned Lossless Image Compression Through Interpolation With Low Complexity

With the increasing popularity of deep learning in image processing, man...

Accelerated Deep Lossless Image Coding with Unified Paralleleized GPU Coding Architecture

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

Learned Iterative Decoding for Lossy Image Compression Systems

For lossy image compression systems, we develop an algorithm called iter...

Comprehensive Complexity Assessment of Emerging Learned Image Compression on CPU and GPU

Learned Compression (LC) is the emerging technology for compressing imag...

Lossless Layout Image Compression Algorithms for Electron-Beam Direct-Write Lithography

Electron-beam direct-write (EBDW) lithography systems must in the future...

Leveraging progressive model and overfitting for efficient learned image compression

Deep learning is overwhelmingly dominant in the field of computer vision...

Learned Image Compression with Separate Hyperprior Decoders

Learned image compression techniques have achieved considerable developm...