# Improving Complex Moir'e Removal with Generative Supervision

arXiv: https://arxiv.org/abs/2608.17883 · HTML: https://mlsanity.com/paper/2608.17883/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [FlowFormer: A Transformer Architecture for Optical Flow](https://mlsanity.com/paper/2203.16194/) (2022)
- [GlueStick: Robust Image Matching by Sticking Points and Lines Together](https://mlsanity.com/paper/2304.02008/) (2023)
- [Image Demoireing with Learnable Bandpass Filters](https://mlsanity.com/paper/2004.00406/) (2020)
- [Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption](https://mlsanity.com/paper/2503.11221/) (2025)
- [Moir'e Photo Restoration Using Multiresolution Convolutional Neural Networks](https://mlsanity.com/paper/1805.02996/) (2018)
- [Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing](https://mlsanity.com/paper/2207.09935/) (2022)
- [AIM 2019 Challenge on Image Demoireing: Dataset and Study](https://mlsanity.com/paper/1911.02498/) (2019)
- [Recaptured Raw Screen Image and Video Demoir'eing via Channel and Spatial Modulations](https://mlsanity.com/paper/2310.20332/) (2023)
- [RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models](https://mlsanity.com/paper/2603.25502/) (2026)
- [Learning Image Demoireing from Unpaired Real Data](https://mlsanity.com/paper/2401.02719/) (2024)
- [UniDemoir'e: Towards Universal Image Demoir'eing with Data Generation and Synthesis](https://mlsanity.com/paper/2502.06324/) (2025)
- [Image Demoir'eing Using Dual Camera Fusion on Mobile Phones](https://mlsanity.com/paper/2506.08361/) (2025)
- [Combined Flicker-banding and Moire Removal for Screen-Captured Images](https://mlsanity.com/paper/2602.01559/) (2026)
- [GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration](https://mlsanity.com/paper/2605.31039/) (2026)

## Abstract (arXiv)

The availability of high-quality paired data is essential for training learning-based image demoir'eing models. However, it remains challenging for existing datasets to encompass the complex moir'e patterns captured in uncontrolled real-world scenarios. Such degradations typically manifest as large-scale, multicolored moir'e patterns. Moreover, these patterns frequently occur in images for which clean counterparts are difficult to obtain, such as photographs acquired from public displays or existing online resources. In this work, we propose a novel data engine designed to improve the removal of complex moir'e patterns by generating training supervision. Specifically, we initially collect real-world images containing complex moir'e patterns and localize the corresponding screen regions. Multiple image-conditioned generative foundation models are subsequently deployed to produce candidate references. To establish reliable supervision, these candidates are subjected to patch-level quality control to filter and select the optimal results. Based on this systematic paradigm, we construct the WildMoir'e dataset, which contains 6.8K moir'e-GT training pairs. For evaluation, we additionally build an independent test set comprising ~250 pairs with captured clean ground truth. Extensive experiments on ESDNet, SDXL, and Qwen-Image-Edit demonstrate that the proposed generative supervision consistently improves the performance of complex moir'e removal.