paper-with-me

홈 › Papers

Learning Multi-scale Spatial-frequency Features for Image Denoising

2025-06-19 · Xu Zhao, Chen Zhao, Xiantao Hu, Hongliang Zhang, Ying Tai, Jian Yang

Recent advancements in multi-scale architectures have demonstrated exceptional performance in image denoising tasks. However, existing architectures mainly depends on a fixed single-input single-output Unet architecture, ignoring the multi-scale representations of pixel level. In addition, previous methods treat the frequency domain uniformly, ignoring the different characteristics of high-frequency and low-frequency noise. In this paper, we propose a novel multi-scale adaptive dual-domain network (MADNet) for image denoising. We use image pyramid inputs to restore noise-free results from low-resolution images. In order to realize the interaction of high-frequency and low-frequency information, we design an adaptive spatial-frequency learning unit (ASFU), where a learnable mask is used to separate the information into high-frequency and low-frequency components. In the skip connections, we design a global feature fusion block to enhance the features at different scales. Extensive experiments on both synthetic and real noisy image datasets verify the effectiveness of MADNet compared with current state-of-the-art denoising approaches.

📄 PDF Abstract BibTeX arXiv:2506.16307

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingImage Denoising

Similar Papers 제목 키워드 기반

Interactive Spatial-Frequency Fusion Mamba for Multi-Modal Image Fusion

2026-02-04 · Yixin Zhu, Long Lv, Pingping Zhang, Xuehu Liu 외 arxiv

Multi-Modal Image Fusion (MMIF) aims to combine images from different modalities to produce fused images, retaining texture details and preserving significant information. Recently, some MMIF methods incorporate frequenc…

Spatial-Frequency Dual Progressive Attention Network For Medical Image Segmentation

2024-06-12 · Zhenhuan Zhou, Along He, Yanlin Wu, Rui Yao 외

In medical images, various types of lesions often manifest significant differences in their shape and texture. Accurate medical image segmentation demands deep learning models with robust capabilities in multi-scale and …

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

Exploring Richer and More Accurate Information via Frequency Selection for Image Restoration

2024-07-12 · Hu Gao, Depeng Dang

Image restoration aims to recover high-quality images from their corrupted counterparts. Many existing methods primarily focus on the spatial domain, neglecting the understanding of frequency variations and ignoring the …

Image Restoration

Dynamic Graph Learning With Content-Guided Spatial-Frequency Relation Reasoning for Deepfake Detection

2023-01-01 · CVPR 2023 1 · YuAn Wang, Kun Yu, Chen Chen, Xiyuan Hu 외

With the springing up of face synthesis techniques, it is prominent in need to develop powerful face forgery detection methods due to security concerns. Some existing methods attempt to employ auxiliary frequency-awa…

DeepFake DetectionFace GenerationFace SwappingGraph Learning+1

SFFR: Spatial-Frequency Feature Reconstruction for Multispectral Aerial Object Detection

2025-11-09 · Xin Zuo, Chenyu Qu, Haibo Zhan, Jifeng Shen 외 arxiv

Recent multispectral object detection methods have primarily focused on spatial-domain feature fusion based on CNNs or Transformers, while the potential of frequency-domain feature remains underexplored. In this work, we…

Multispectral Object Detection