UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis
This addresses the robustness issue in real-world image restoration for applications like photography and computer vision, though it appears incremental as it builds on existing demoiréing methods by improving data diversity.
The paper tackles the problem of image demoiréing, which is challenging due to unpredictable moiré patterns, by proposing UniDemoiré, a universal solution with superior generalization capability, achieved through innovative data generation and synthesis methods that provide vast high-quality training data, resulting in cutting-edge performance as demonstrated in extensive experiments.
Image demoiréing poses one of the most formidable challenges in image restoration, primarily due to the unpredictable and anisotropic nature of moiré patterns. Limited by the quantity and diversity of training data, current methods tend to overfit to a single moiré domain, resulting in performance degradation for new domains and restricting their robustness in real-world applications. In this paper, we propose a universal image demoiréing solution, UniDemoiré, which has superior generalization capability. Notably, we propose innovative and effective data generation and synthesis methods that can automatically provide vast high-quality moiré images to train a universal demoiréing model. Our extensive experiments demonstrate the cutting-edge performance and broad potential of our approach for generalized image demoiréing.