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

2026-02-03

AI Summary

This work proposes the first efficient binary framework tailored for image demoiréing, addressing the high deployment cost of full-precision models and the subpar performance of existing binarization methods. By explicitly modeling the frequency structure and directional characteristics of moiré patterns, the authors introduce a Moiré-Aware Binary Gating (MABG) mechanism and a Shuffle Group Residual Adapter (SGRA) to enable structured sparsity and cross-channel information interaction under 1-bit weights and activations. The proposed method significantly outperforms current binarization approaches across four benchmark datasets, achieving high-quality demoiréing performance while substantially compressing the model size.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Large pretrained models with web data

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.

Problem

• image demoiréing
• binarization
• moiré artifacts
• frequency-dependent degradation
• 1-bit quantization

Innovation

• binary neural network
• image demoireing
• moire-aware binarization
• structured sparsity
• channel gating