Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition
This addresses the problem of removing moiré artifacts in images for applications like photography and computer vision, representing an incremental improvement over existing methods.
The paper tackles image demoiréing by proposing Freqformer, a Transformer-based framework that decomposes moiré patterns into high-frequency textures and low-frequency color distortions for targeted restoration, achieving state-of-the-art performance on benchmarks with a compact model size.
Image demoiréing remains a challenging task due to the complex interplay between texture corruption and color distortions caused by moiré patterns. Existing methods, especially those relying on direct image-to-image restoration, often fail to disentangle these intertwined artifacts effectively. While wavelet-based frequency-aware approaches offer a promising direction, their potential remains underexplored. In this paper, we present Freqformer, a Transformer-based framework specifically designed for image demoiréing through targeted frequency separation. Our method performs an effective frequency decomposition that explicitly splits moiré patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions, which are then handled by a dual-branch architecture tailored to their distinct characteristics. We further propose a learnable Frequency Composition Transform (FCT) module to adaptively fuse the frequency-specific outputs, enabling consistent and high-fidelity reconstruction. To better aggregate the spatial dependencies and the inter-channel complementary information, we introduce a Spatial-Aware Channel Attention (SA-CA) module that refines moiré-sensitive regions without incurring high computational cost. Extensive experiments on various demoiréing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size. The code is publicly available at https://github.com/xyLiu339/Freqformer.