Fabric Image Demoiréing Benchmark from Synthesis to Restoration

2026-06-22

AI Summary

This study addresses the challenge of moiré pattern removal in textile images, a problem exacerbated by the broadband and semi-periodic nature of fabric textures that renders existing methods ineffective. To advance research in this domain, the authors introduce the first comprehensive benchmark for fabric image demoiréing, comprising a physics-driven synthesis framework that generates 16,050 multi-resolution image pairs with controllable moiré intensity. A tailored deep learning baseline model is developed and evaluated on this benchmark, demonstrating superior performance and strong generalization capabilities. The proposed benchmark fills a critical gap in both data availability and standardized evaluation protocols, establishing a reliable foundation for future work on moiré artifact suppression in textile imaging.

Abstract

Fabric moiré is a sampling-induced aliasing artifact caused by the interaction between fine textile patterns and camera sensor grids, producing structured interference that severely degrades image quality. Unlike screen-induced moiré, which stems from strictly periodic display lattices, fabric moiré is intrinsically more challenging due to the broadband and semi-periodic nature of textile weaves. The heavy spectral overlap between intrinsic texture and aliasing components renders fabric demoiréing substantially more ill-posed. Consequently, existing models trained on screen moiré datasets generalize poorly to these complex textile patterns. Despite its practical importance, fabric image demoiréing remains underexplored and lacks standardized benchmarks. We present the first comprehensive benchmark for fabric image demoiréing. To address the difficulty of acquiring pixel-aligned real-world pairs, we develop a physically motivated synthesis framework and construct a large-scale dataset comprising 16,050 paired multi-resolution fabric images with controllable aliasing severity. Furthermore, we customize a baseline model, which establishes promising performance on the proposed benchmark dataset with strong generalization ability. Our benchmark provides a standardized platform for advancing research in fabric image demoiréing.

Problem

• fabric moiré
• image demoiréing
• aliasing artifact
• texture interference
• benchmark dataset

Innovation

• fabric demoiréing
• physically motivated synthesis
• benchmark dataset
• aliasing artifact
• texture restoration