UniDemoir\'e: Towards Universal Image Demoir\'eing with Data Generation and Synthesis

TL;DR

UniDemoiré introduces a universal image demoiréing approach that leverages advanced data generation and synthesis techniques to significantly improve generalization across diverse moiré patterns, outperforming existing methods.

Contribution

The paper presents novel data generation and synthesis methods enabling training of a universal demoiréing model with high-quality diverse moiré images, enhancing robustness and generalization.

Findings

Achieves state-of-the-art demoiréing performance across multiple datasets.

Demonstrates superior generalization to unseen moiré patterns.

Shows potential for real-world application robustness.

Abstract

Image demoir\'eing poses one of the most formidable challenges in image restoration, primarily due to the unpredictable and anisotropic nature of moir\'e patterns. Limited by the quantity and diversity of training data, current methods tend to overfit to a single moir\'e domain, resulting in performance degradation for new domains and restricting their robustness in real-world applications. In this paper, we propose a universal image demoir\'eing solution, UniDemoir\'e, which has superior generalization capability. Notably, we propose innovative and effective data generation and synthesis methods that can automatically provide vast high-quality moir\'e images to train a universal demoir\'eing model. Our extensive experiments demonstrate the cutting-edge performance and broad potential of our approach for generalized image demoir\'eing.