# Moir'eNet: A Compact Dual-Domain Network for Image Demoir'eing

arXiv: https://arxiv.org/abs/2509.18910 · HTML: https://mlsanity.com/paper/2509.18910/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Builds on (most cited first, 10 of 10)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [Searching Central Difference Convolutional Networks for Face Anti-Spoofing](https://mlsanity.com/paper/2003.04092/) (2020)
- [DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention](https://mlsanity.com/paper/2301.04805/) (2023)
- [Wavelet Convolutions for Large Receptive Fields](https://mlsanity.com/paper/2407.05848/) (2024)
- [Wavelet-Based Dual-Branch Network for Image Demoireing](https://mlsanity.com/paper/2007.07173/) (2020)
- [Multi-scale Dynamic Feature Encoding Network for Image Demoireing](https://mlsanity.com/paper/1909.11947/) (2019)
- [AIM 2019 Challenge on Image Demoireing: Methods and Results](https://mlsanity.com/paper/1911.03461/) (2019)
- [FPANet: Frequency-based Video Demoireing using Frame-level Post Alignment](https://mlsanity.com/paper/2301.07330/) (2023)

## Abstract (arXiv)

Moir'e patterns arise from spectral aliasing between display pixel lattices and camera sensor grids, manifesting as anisotropic, multi-scale artifacts that pose significant challenges for digital image demoir'eing. We propose Moir'eNet, a convolutional neural U-Net-based framework that synergistically integrates frequency and spatial domain features for effective artifact removal. Moir'eNet introduces two key components: a Directional Frequency-Spatial Encoder (DFSE) that discerns moir'e orientation via directional difference convolution, and a Frequency-Spatial Adaptive Selector (FSAS) that enables precise, feature-adaptive suppression. Extensive experiments demonstrate that Moir'eNet achieves state-of-the-art performance on public and actively used datasets while being highly parameter-efficient. With only 5.513M parameters, representing a 48% reduction compared to ESDNet-L, Moir'eNet combines superior restoration quality with parameter efficiency, making it well-suited for resource-constrained applications including smartphone photography, industrial imaging, and augmented reality.