Moiré Zero: An Efficient and High-Performance Neural Architecture for Moiré Removal

2025-07-30

AI Summary

Moiré patterns arise from frequency aliasing between periodic structures in images and sensor sampling, severely degrading image quality in consumer photography and industrial inspection. Existing CNN-based methods suffer from limited receptive fields and struggle to model the multi-scale, multi-directional, and chromatic characteristics of Moiré artifacts. This paper proposes MZNet—a U-shaped architecture featuring a novel multi-scale dual-attention mechanism and a multi-shape large-kernel convolution module, jointly enhancing global contextual modeling and local structural perception. Additionally, feature-fusion skip connections are introduced to improve fine-detail recovery. Evaluated on both high- and low-resolution benchmark datasets, MZNet achieves state-of-the-art performance while requiring significantly fewer parameters and lower computational cost than competing approaches, demonstrating superior efficiency and practicality.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Mixture of Experts (MoE)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Moiré patterns, caused by frequency aliasing between fine repetitive structures and a camera sensor's sampling process, have been a significant obstacle in various real-world applications, such as consumer photography and industrial defect inspection. With the advancements in deep learning algorithms, numerous studies-predominantly based on convolutional neural networks-have suggested various solutions to address this issue. Despite these efforts, existing approaches still struggle to effectively eliminate artifacts due to the diverse scales, orientations, and color shifts of moiré patterns, primarily because the constrained receptive field of CNN-based architectures limits their ability to capture the complex characteristics of moiré patterns. In this paper, we propose MZNet, a U-shaped network designed to bring images closer to a 'Moire-Zero' state by effectively removing moiré patterns. It integrates three specialized components: Multi-Scale Dual Attention Block (MSDAB) for extracting and refining multi-scale features, Multi-Shape Large Kernel Convolution Block (MSLKB) for capturing diverse moiré structures, and Feature Fusion-Based Skip Connection for enhancing information flow. Together, these components enhance local texture restoration and large-scale artifact suppression. Experiments on benchmark datasets demonstrate that MZNet achieves state-of-the-art performance on high-resolution datasets and delivers competitive results on lower-resolution dataset, while maintaining a low computational cost, suggesting that it is an efficient and practical solution for real-world applications. Project page: https://sngryonglee.github.io/MoireZero

Problem

• Removing moiré patterns from images efficiently
• Handling diverse moiré scales and orientations
• Reducing artifacts while maintaining low computational cost

Innovation

• U-shaped network for moiré removal
• Multi-Scale Dual Attention Block
• Multi-Shape Large Kernel Convolution