提出针对摩尔纹特性的二值化图像去摩尔纹方法，提升模型压缩效率。
BinaryDemoire: Moiré-Aware Binarization for Image Demoiréing
- 设计频域感知二值门，动态调节通道响应以适配摩尔纹频率结构
- 在四个数据集上达到优于现有二值化方法的去摩尔纹效果
- 适合部署资源受限场景下的图像去摩尔纹任务
图像去摩尔纹旨在消除重拍图像中的结构化摩尔纹伪影，其退化具有高度频域依赖性，且在不同尺度和方向上变化显著。尽管近期深度网络实现了高质量重建，但其全精度设计在部署时仍成本高昂。二值化通过将激活值和权重均量化至1比特，提供极致压缩。然而，该技术在去摩尔纹领域研究极少，且直接应用性能不佳。本文提出BinaryDemoire，一种显式适应摩尔纹频域结构的二值化去摩尔纹框架。首先，引入摩尔纹感知二值门（MABG），联合提取轻量级频域描述符与激活统计信息，预测通道级门控系数以调控二值卷积响应的聚合。其次，设计混洗分组残差适配器（SGRA），实现结构化稀疏捷径对齐，并引入交错混合机制促进不同通道分区间的特征交互。在四个基准数据集上的大量实验表明，所提BinaryDemoire超越当前二值化方法。代码已开源：https://github.com/zhengchen1999/BinaryDemoire。
原文摘要 · Abstract (English)
Image demoiréing aims to remove structured moiré 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 demoiréing and performs poorly when naively applied. In this work, we propose BinaryDemoire, a binarized demoiréing framework that explicitly accommodates the frequency structure of moiré degradations. First, we introduce a moiré-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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。