The Performance of Compression-Based Denoisers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Song, Dan, Özgür, Ayfer, Weissman, Tsachy
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915679251202048
author Song, Dan
Özgür, Ayfer
Weissman, Tsachy
author_facet Song, Dan
Özgür, Ayfer
Weissman, Tsachy
contents We consider a denoiser that reconstructs a stationary ergodic source by lossily compressing samples of the source observed through a memoryless noisy channel. Prior work on compression-based denoising has been limited to additive noise channels. We extend this framework to general discrete memoryless channels by deliberately choosing the distortion measure for the lossy compressor to match the channel conditional distribution. By bounding the deviation of the empirical joint distribution of the source, observation, and denoiser outputs from satisfying a Markov property, we give an exact characterization of the loss achieved by such a denoiser. Consequences of these results are explicitly demonstrated in special cases, including for MSE and Hamming loss. A comparison is made to an indirect rate-distortion perspective on the problem.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14539
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Performance of Compression-Based Denoisers
Song, Dan
Özgür, Ayfer
Weissman, Tsachy
Information Theory
We consider a denoiser that reconstructs a stationary ergodic source by lossily compressing samples of the source observed through a memoryless noisy channel. Prior work on compression-based denoising has been limited to additive noise channels. We extend this framework to general discrete memoryless channels by deliberately choosing the distortion measure for the lossy compressor to match the channel conditional distribution. By bounding the deviation of the empirical joint distribution of the source, observation, and denoiser outputs from satisfying a Markov property, we give an exact characterization of the loss achieved by such a denoiser. Consequences of these results are explicitly demonstrated in special cases, including for MSE and Hamming loss. A comparison is made to an indirect rate-distortion perspective on the problem.
title The Performance of Compression-Based Denoisers
topic Information Theory
url https://arxiv.org/abs/2512.14539