BinaryDemoire: Moir\'e-Aware Binarization for Image Demoir\'eing

TL;DR

BinaryDemoire introduces a frequency-aware binarization framework for image demoiréing, effectively reducing model size while maintaining high restoration quality by explicitly modeling moiré artifacts.

Contribution

The paper proposes a novel moiré-aware binary gate and a shuffle-grouped residual adapter to improve binarized demoiréing models, addressing the challenge of frequency-dependent degradations.

Findings

Outperforms existing binarization methods on four benchmarks.

Effectively captures frequency structure of moiré artifacts.

Maintains high-quality image restoration with reduced model complexity.

Abstract

Image demoir\'eing aims to remove structured moir\'e artifacts in recaptured imagery, where degradations are highly frequency-dependent and vary across scales and directions. While recent deep networks achieve high-quality restoration, their full-precision designs remain costly for deployment. Binarization offers an extreme compression regime by quantizing both activations and weights to 1-bit. Yet, it has been rarely studied for demoir\'eing and performs poorly when naively applied. In this work, we propose BinaryDemoire, a binarized demoir\'eing framework that explicitly accommodates the frequency structure of moir\'e degradations. First, we introduce a moir\'e-aware binary gate (MABG) that extracts lightweight frequency descriptors together with activation statistics. It predicts channel-wise gating coefficients to condition the aggregation of binary convolution responses. Second, we design a shuffle-grouped residual adapter (SGRA) that performs structured sparse shortcut alignment. It further integrates interleaved mixing to promote information exchange across different channel partitions. Extensive experiments on four benchmarks demonstrate that the proposed BinaryDemoire surpasses current binarization methods. Code: https://github.com/zhengchen1999/BinaryDemoire.