Moir\'e Zero: An Efficient and High-Performance Neural Architecture for Moir\'e Removal

TL;DR

Moiré Zero introduces a novel neural network architecture that effectively removes moiré patterns from images by capturing multi-scale and diverse pattern features, achieving state-of-the-art results with high efficiency.

Contribution

The paper presents MZNet, a U-shaped network with specialized blocks for multi-scale feature extraction and large kernel convolution, improving moiré removal over existing CNN-based methods.

Findings

Achieves state-of-the-art performance on high-resolution datasets.

Maintains low computational cost for practical applications.

Performs competitively on lower-resolution datasets.

Abstract

Moir\'e 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 moir\'e patterns, primarily because the constrained receptive field of CNN-based architectures limits their ability to capture the complex characteristics of moir\'e patterns. In this paper, we propose MZNet, a U-shaped network designed to bring images closer to a 'Moire-Zero' state by effectively removing moir\'e 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 moir\'e 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