Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Xiaoyang, Qiu, Bolin, Cao, Jiezhang, Chen, Zheng, Zhang, Yulun, Yang, Xiaokang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912392994095104
author Liu, Xiaoyang
Qiu, Bolin
Cao, Jiezhang
Chen, Zheng
Zhang, Yulun
Yang, Xiaokang
author_facet Liu, Xiaoyang
Qiu, Bolin
Cao, Jiezhang
Chen, Zheng
Zhang, Yulun
Yang, Xiaokang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19120
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition
Liu, Xiaoyang
Qiu, Bolin
Cao, Jiezhang
Chen, Zheng
Zhang, Yulun
Yang, Xiaokang
Computer Vision and Pattern Recognition
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.
title Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.19120