mlsanityData to 14 Oct 2026

Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoising

arXiv 2412.16645 ↗First posted 21 Dec 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Existing single-image denoising algorithms often struggle to restore details when dealing with complex noisy images. The introduction of near-infrared (NIR) images offers new possibilities for RGB image denoising. However, due to the inconsistency between NIR and RGB images, the existing works still struggle to balance the contributions of two fields in the process of image fusion. In response to this, in this paper, we develop a cross-field Frequency Correlation Exploiting Network (FCENet) for NIR-assisted image denoising. We first propose the frequency correlation prior based on an in-depth statistical frequency analysis of NIR-RGB image pairs. The prior reveals the complementary correlation of NIR and RGB images in the frequency domain. Leveraging frequency correlation prior, we then establish a frequency learning framework composed of Frequency Dynamic Selection Mechanism (FDSM) and Frequency Exhaustive Fusion Mechanism (FEFM). FDSM dynamically selects complementary information from NIR and RGB images in the frequency domain, and FEFM strengthens the control of common and differential features during the fusion process of NIR and RGB features. Extensive experiments on simulated and real data validate that the proposed method outperforms other state-of-the-art methods. The code will be released at https://github.com/yuchenwang815/FCENet.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 40 of its 56 references that are in the map. First posted on arXiv 21 Dec 2024.

Builds on

40 of 56 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  5. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  6. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  7. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  8. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 866
  9. 2021Multi-Stage Progressive Image Restorationcited by 816
  10. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 510
  11. 2019Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networkscited by 368
  12. 2019Dynamic Convolution: Attention over Convolution Kernelscited by 356
28 more
  1. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 326
  2. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 276
  3. 2020Focal Frequency Loss for Image Reconstruction and Synthesiscited by 206
  4. 2019Real Image Denoising with Feature Attentioncited by 176
  5. 2022Efficient Frequency Domain-based Transformers for High-Quality Image Deblurringcited by 165
  6. 2019Deep Learning on Image Denoising: An overviewcited by 128
  7. 2021CAT: Cross Attention in Vision Transformercited by 92
  8. 2020Unsupervised Real-world Image Super Resolution via Domain-distance Aware Trainingcited by 83
  9. 2019Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusioncited by 79
  10. 2020NBNet: Noise Basis Learning for Image Denoising with Subspace Projectioncited by 77
  11. 2022HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imagingcited by 66
  12. 2023Zero-Shot Noise2Noise: Efficient Image Denoising without any Datacited by 61
  13. 2019Deformable Kernel Networks for Joint Image Filteringcited by 59
  14. 2021Decoupled Dynamic Filter Networkscited by 53
  15. 2020NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Resultscited by 51
  16. 2023Xformer: Hybrid X-Shaped Transformer for Image Denoisingcited by 37
  17. 2021SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurringcited by 26
  18. 2022Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modelingcited by 23
  19. 2023FFT-based Dynamic Token Mixer for Visioncited by 22
  20. 2023DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Priorcited by 19
  21. 2023Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensemblingcited by 17
  22. 2023Mutual-Guided Dynamic Network for Image Fusioncited by 14
  23. 2023In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imagingcited by 8
  24. 2019Stereoscopic Dark Flash for Low-light Photographycited by 7
  25. 2020An Integrated Enhancement Solution for 24-hour Colorful Imagingcited by 5
  26. 2022A Dual Sensor Computational Camera for High Quality Dark Videographycited by 4
  27. 2024NIR-Assisted Image Denoising: A Selective Fusion Approach and A Real-World Benchmark Datasetcited by 4
  28. 2024Exploiting Frequency Correlation for Hyperspectral Image Reconstructioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025PAD: Phase-Amplitude Decoupling Fusion for Multi-Modal Land Cover Classificationcited by 2
  2. 2026Toward Robust and 3D-Aware RGB-NIR Imaging in the Darkcited by 2
  3. 2026CP-WSP: A Declarative CP-SAT Framework for Configurable Multi-Constraint Workforce Schedulingcited by 1
  4. 2025Hybrid-Domain Synergistic Transformer for Hyperspectral Image Denoisingcited by 0
  5. 2026Frequency-Decomposed INR for NIR-Assisted Low-Light RGB Image Denoisingcited by 0