Guiding WaveMamba with Frequency Maps for Image Debanding

TL;DR

This paper introduces a novel banding restoration method using Wavelet State Space Model and frequency maps, improving visual quality in compressed images with banding artifacts, and provides a benchmark for existing methods.

Contribution

It presents a new post-processing approach for image debanding that effectively suppresses artifacts while preserving textures, along with a comprehensive benchmark of existing methods.

Findings

The proposed method outperforms state-of-the-art in suppressing banding artifacts.

It preserves high-frequency details better than previous approaches.

Experimental results show significant visual quality improvements.

Abstract

Compression at low bitrates in modern codecs often introduces banding artifacts, especially in smooth regions such as skies. These artifacts degrade visual quality and are common in user-generated content due to repeated transcoding. We propose a banding restoration method that employs the Wavelet State Space Model and a frequency masking map to preserve high-frequency details. Furthermore, we provide a benchmark of open-source banding restoration methods and evaluate their performance on two public banding image datasets. Experimentation on the available datasets suggests that the proposed post-processing approach effectively suppresses banding compared to the state-of-the-art method (a DBI value of 0.082 on BAND-2k) while preserving image textures. Visual inspections of the results confirm this. Code and supplementary material are available at: https://github.com/xinyiW915/Debanding-PCS2025.