Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoising
- URL: http://arxiv.org/abs/2412.16645v1
- Date: Sat, 21 Dec 2024 14:31:36 GMT
- Title: Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoising
- Authors: Yuchen Wang, Hongyuan Wang, Lizhi Wang, Xin Wang, Lin Zhu, Wanxuan Lu, Hua Huang,
- Abstract summary: 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.
We then establish a frequency learning framework composed of Frequency Dynamic Selection Mechanism (FDSM) and Frequency Exhaustive Fusion Mechanism (FEFM)
- Score: 27.54777017705553
- License:
- Abstract: 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 of NIR and RGB features. Extensive experiments on simulated and real data validate that our method outperforms various state-of-the-art methods in terms of image quality and computational efficiency. The code will be released to the public.
Related papers
- Contourlet Refinement Gate Framework for Thermal Spectrum Distribution Regularized Infrared Image Super-Resolution [54.293362972473595]
Image super-resolution (SR) aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts.
Current approaches to address SR tasks are either dedicated to extracting RGB image features or assuming similar degradation patterns.
We propose a Contourlet refinement gate framework to restore infrared modal-specific features while preserving spectral distribution fidelity.
arXiv Detail & Related papers (2024-11-19T14:24:03Z) - FreqINR: Frequency Consistency for Implicit Neural Representation with Adaptive DCT Frequency Loss [5.349799154834945]
This paper introduces Frequency Consistency for Implicit Neural Representation (FreqINR), an innovative Arbitrary-scale Super-resolution method.
During training, we employ Adaptive Discrete Cosine Transform Frequency Loss (ADFL) to minimize the frequency gap between HR and ground-truth images.
During inference, we extend the receptive field to preserve spectral coherence between low-resolution (LR) and ground-truth images.
arXiv Detail & Related papers (2024-08-25T03:53:17Z) - Exploiting Frequency Correlation for Hyperspectral Image Reconstruction [21.71115793248267]
Deep priors have emerged as potent methods in hyperspectral image (HSI) reconstruction.
We propose a Hyperspectral Frequency Correlation (HFC) prior rooted in in-depth statistical frequency analyses of existent HSI datasets.
We then establish the frequency domain learning composed of a Spectral-wise self-Attention of Frequency (SAF) and a Spectral-spatial Interaction of Frequency (SIF)
arXiv Detail & Related papers (2024-06-02T09:36:37Z) - NIR-Assisted Image Denoising: A Selective Fusion Approach and A Real-World Benchmark Dataset [53.79524776100983]
Leveraging near-infrared (NIR) images to assist visible RGB image denoising shows the potential to address this issue.
Existing works still struggle with taking advantage of NIR information effectively for real-world image denoising.
We propose an efficient Selective Fusion Module (SFM), which can be plug-and-played into the advanced denoising networks.
arXiv Detail & Related papers (2024-04-12T14:54:26Z) - Cooperative Colorization: Exploring Latent Cross-Domain Priors for NIR
Image Spectrum Translation [5.28882362783108]
Near-infrared (NIR) image spectrum translation is a challenging problem with many promising applications.
We propose a cooperative learning paradigm that colorizes NIR images in parallel with another proxy grayscale colorization task.
Experiments show that our proposed cooperative learning framework produces satisfactory spectrum translation outputs with diverse colors and rich textures.
arXiv Detail & Related papers (2023-08-07T07:02:42Z) - Denoising Diffusion Models for Plug-and-Play Image Restoration [135.6359475784627]
This paper proposes DiffPIR, which integrates the traditional plug-and-play method into the diffusion sampling framework.
Compared to plug-and-play IR methods that rely on discriminative Gaussian denoisers, DiffPIR is expected to inherit the generative ability of diffusion models.
arXiv Detail & Related papers (2023-05-15T20:24:38Z) - High Dynamic Range Image Quality Assessment Based on Frequency Disparity [78.36555631446448]
An image quality assessment (IQA) algorithm based on frequency disparity for high dynamic range ( HDR) images is proposed.
The proposed LGFM can provide a higher consistency with the subjective perception compared with the state-of-the-art HDR IQA methods.
arXiv Detail & Related papers (2022-09-06T08:22:13Z) - TBNet:Two-Stream Boundary-aware Network for Generic Image Manipulation
Localization [49.521622399483846]
We propose a novel end-to-end two-stream boundary-aware network (abbreviated as TBNet) for generic image manipulation localization.
The proposed TBNet can significantly outperform state-of-the-art generic image manipulation localization methods in terms of both MCC and F1.
arXiv Detail & Related papers (2021-08-10T08:22:05Z) - Wavelet-Based Network For High Dynamic Range Imaging [64.66969585951207]
Existing methods, such as optical flow based and end-to-end deep learning based solutions, are error-prone either in detail restoration or ghosting artifacts removal.
In this work, we propose a novel frequency-guided end-to-end deep neural network (FNet) to conduct HDR fusion in the frequency domain, and Wavelet Transform (DWT) is used to decompose inputs into different frequency bands.
The low-frequency signals are used to avoid specific ghosting artifacts, while the high-frequency signals are used for preserving details.
arXiv Detail & Related papers (2021-08-03T12:26:33Z) - Generation of the NIR spectral Band for Satellite Images with
Convolutional Neural Networks [0.0]
Deep neural networks allow generating artificial spectral information, such as for the image colorization problem.
We study the generative adversarial network (GAN) approach in the task of the NIR band generation using just RGB channels of high-resolution satellite imagery.
arXiv Detail & Related papers (2021-06-13T15:14:57Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.