Frequency-Decomposed INR for NIR-Assisted Low-Light RGB Image Denoising
- URL: http://arxiv.org/abs/2604.16800v1
- Date: Sat, 18 Apr 2026 03:12:51 GMT
- Title: Frequency-Decomposed INR for NIR-Assisted Low-Light RGB Image Denoising
- Abstract summary: This paper proposes a Near Infrared (NIR) aided low light image restoration method based on Frequency Decoupled Implicit Neural Representation (FDINR)<n>We decompose images into distinct frequency components via multi-scale wavelet transforms and construct a dual-branch implicit neural representation framework.<n> Experimental results demonstrate that FD-INR not only effectively restores image luminance consistency and structural details but also, benefitting from its implicit continuous representation, outperforms existing methods in arbitrary-resolution reconstruction tasks.
- Score: 3.1407264198113936
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Addressing the issues of severe noise and high frequency structural degradation in visible images under low-light conditions, this paper proposes a Near Infrared (NIR) aided low light image restoration method based on Frequency Decoupled Implicit Neural Representation (FDINR). Based on the statistical prior of RGB-NIR cross-modal frequency correlations, specifically that low-frequency RGB signals are more reliable, whereas high frequency NIR signals exhibit higher correlation, we explicitly decompose images into distinct frequency components via multi-scale wavelet transforms and construct a dual-branch implicit neural representation framework. Within this framework, we design a cross modal differentiated frequency supervision mechanism, leveraging low light RGB to guide the reconstruction of low frequency luminance and color, and utilizing high-SNR NIR signals to constrain the generation of high frequency texture details, thereby achieving complementary advantages in the frequency domain. Furthermore, an uncertainty-based adaptive weighting loss function is introduced to automatically balance the contributions of different frequency tasks, solving the problems of color distortion and artifacts caused by rigid fusion in the spatial domain common in traditional methods. Experimental results demonstrate that FD-INR not only effectively restores image luminance consistency and structural details but also, benefitting from its implicit continuous representation, outperforms existing methods in arbitrary-resolution reconstruction tasks, significantly enhancing the reliability of low light perception.
Related papers
- MFEN:Multi-Frequency Expert Network for Visible-Infrared Person Re-ID [54.607429411644716]
Visible-infrared person re-identification (VI-ReID) is challenging due to the large modality discrepancy between visible and infrared images.<n>We propose a Multi-Frequency Expert Network (MFEN) that enables multi-frequency modulation and adaptively combines different bands.
arXiv Detail & Related papers (2026-06-10T13:16:22Z) - Efficient RAW Image Deblurring with Adaptive Frequency Modulation [12.675989208670664]
Deblurring RAW images presents unique challenges, particularly in handling frequency-dependent blur.<n>We propose Frequency Enhanced Network (FrENet), a framework specifically designed for RAW-to-RAW deblurring.<n> Experimental results demonstrate that FrENet surpasses state-of-the-art deblurring methods in RAW image deblurring.
arXiv Detail & Related papers (2025-05-30T09:46:39Z) - Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoising [27.54777017705553]
We develop a cross-field Frequency Correlation Exploiting Network (FCENet) for NIR-assisted image denoising.<n>We first propose the frequency correlation prior based on an in-depth statistical frequency analysis of NIR-RGB image pairs.<n>We then establish a frequency learning framework composed of Frequency Dynamic Selection Mechanism (FDSM) and Frequency Exhaustive Fusion Mechanism (FEFM)
arXiv Detail & Related papers (2024-12-21T14:31:36Z) - 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) - 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.<n>Existing works still struggle with taking advantage of NIR information effectively for real-world image denoising.<n>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) - Low-Light Enhancement in the Frequency Domain [24.195131201768096]
Decreased visibility, intensive noise, and biased color are the common problems existing in low-light images.
We propose a novel residual recurrent multi-wavelet convolutional neural network R2-MWCNN learned in the frequency domain.
This end-to-end trainable network utilizes a multi-level discrete wavelet transform to divide input feature maps into distinct frequencies, resulting in a better denoise impact.
arXiv Detail & Related papers (2023-06-29T08:39:34Z) - 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) - Tuning IR-cut Filter for Illumination-aware Spectral Reconstruction from
RGB [84.1657998542458]
It has been proven that the reconstruction accuracy relies heavily on the spectral response of the RGB camera in use.
This paper explores the filter-array based color imaging mechanism of existing RGB cameras, and proposes to design the IR-cut filter properly for improved spectral recovery.
arXiv Detail & Related papers (2021-03-26T19:42:21Z) - Frequency Consistent Adaptation for Real World Super Resolution [64.91914552787668]
We propose a novel Frequency Consistent Adaptation (FCA) that ensures the frequency domain consistency when applying Super-Resolution (SR) methods to the real scene.
We estimate degradation kernels from unsupervised images and generate the corresponding Low-Resolution (LR) images.
Based on the domain-consistent LR-HR pairs, we train easy-implemented Convolutional Neural Network (CNN) SR models.
arXiv Detail & Related papers (2020-12-18T08:25:39Z)
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.