Toward Textual Transform Coding

05/03/2023
by   Tsachy Weissman, et al.
0

Inspired by recent work on compression with and for young humans, the success of transform-based approaches to information processing, and the rise of powerful language-based AI, we propose textual transform coding. It shares some of its key properties with traditional transform-based coding underlying much of our current multimedia compression technologies. It can form the basis for compression at bit rates until recently considered uselessly low, and for boosting human satisfaction from reconstructions at more traditional bit rates.

READ FULL TEXT

page 4

page 5

research
01/28/2015

A Discrete Tchebichef Transform Approximation for Image and Video Coding

In this paper, we introduce a low-complexity approximation for the discr...
research
08/24/2020

Lossy Image Compression with Normalizing Flows

Deep learning based image compression has recently witnessed exciting pr...
research
03/04/2017

Generative Compression

Traditional image and video compression algorithms rely on hand-crafted ...
research
11/09/2012

Time Complexity Analysis of Binary Space Partitioning Scheme for Image Compression

Segmentation-based image coding methods provide high compression ratios ...
research
08/12/2019

Committee Draft of JPEG XL Image Coding System

JPEG XL is a practical approach focused on scalable web distribution and...
research
06/17/2022

Lossy Compression with Gaussian Diffusion

We describe a novel lossy compression approach called DiffC which is bas...
research
03/09/2022

Neural Data-Dependent Transform for Learned Image Compression

Learned image compression has achieved great success due to its excellen...

Please sign up or login with your details

Forgot password? Click here to reset